Upload folder using huggingface_hub (#3)
Browse files- 11f9411b9b4be116ac92c1dfd08b85b07cdcae1b5da86ee4c07e97384dad47ae (ef0bf7bb2cfb1ca0392b57bc4d0d97a9ac4ef608)
- 0d881fc9c8834ad595b1ef269a1ceb9da2055e8c28f9c6a784c331afe0ada667 (d9ea2f1d0d45a10b5788c2f266fe676624590abd)
- README.md +8 -10
- config.json +12 -13
- model.safetensors +2 -2
- model.safetensors.index.json +1 -767
- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +258 -1
README.md
CHANGED
|
@@ -1,22 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
|
|
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
license: gemma
|
| 5 |
-
pipeline_tag: text-generation
|
| 6 |
tags:
|
| 7 |
-
-
|
|
|
|
|
|
|
|
|
|
| 8 |
- mlx
|
| 9 |
-
- mlx
|
| 10 |
-
extra_gated_heading: Access Gemma on Hugging Face
|
| 11 |
-
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
| 12 |
-
agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
|
| 13 |
-
Face and click below. Requests are processed immediately.
|
| 14 |
-
extra_gated_button_content: Acknowledge license
|
| 15 |
---
|
| 16 |
|
| 17 |
# TeunS/Geert
|
| 18 |
|
| 19 |
-
The Model [TeunS/Geert](https://huggingface.co/TeunS/Geert) was converted to MLX format from [
|
| 20 |
|
| 21 |
## Use with mlx
|
| 22 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/gemma-2-2b-it
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
library_name: transformers
|
| 6 |
license: gemma
|
|
|
|
| 7 |
tags:
|
| 8 |
+
- unsloth
|
| 9 |
+
- transformers
|
| 10 |
+
- gemma2
|
| 11 |
+
- gemma
|
| 12 |
- mlx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# TeunS/Geert
|
| 16 |
|
| 17 |
+
The Model [TeunS/Geert](https://huggingface.co/TeunS/Geert) was converted to MLX format from [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) using mlx-lm version **0.19.3**.
|
| 18 |
|
| 19 |
## Use with mlx
|
| 20 |
|
config.json
CHANGED
|
@@ -7,31 +7,30 @@
|
|
| 7 |
"attn_logit_softcapping": 50.0,
|
| 8 |
"bos_token_id": 2,
|
| 9 |
"cache_implementation": "hybrid",
|
| 10 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
| 11 |
"final_logit_softcapping": 30.0,
|
| 12 |
"head_dim": 256,
|
| 13 |
"hidden_act": "gelu_pytorch_tanh",
|
| 14 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
-
"hidden_size":
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size":
|
| 18 |
"max_position_embeddings": 8192,
|
| 19 |
"model_type": "gemma2",
|
| 20 |
-
"num_attention_heads":
|
| 21 |
-
"num_hidden_layers":
|
| 22 |
-
"num_key_value_heads":
|
| 23 |
"pad_token_id": 0,
|
| 24 |
-
"
|
| 25 |
-
"group_size": 64,
|
| 26 |
-
"bits": 4
|
| 27 |
-
},
|
| 28 |
-
"query_pre_attn_scalar": 224,
|
| 29 |
"rms_norm_eps": 1e-06,
|
| 30 |
"rope_theta": 10000.0,
|
| 31 |
"sliding_window": 4096,
|
| 32 |
-
"sliding_window_size": 4096,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
-
"transformers_version": "4.
|
|
|
|
| 35 |
"use_cache": true,
|
| 36 |
"vocab_size": 256000
|
| 37 |
}
|
|
|
|
| 7 |
"attn_logit_softcapping": 50.0,
|
| 8 |
"bos_token_id": 2,
|
| 9 |
"cache_implementation": "hybrid",
|
| 10 |
+
"eos_token_id": [
|
| 11 |
+
1,
|
| 12 |
+
107
|
| 13 |
+
],
|
| 14 |
"final_logit_softcapping": 30.0,
|
| 15 |
"head_dim": 256,
|
| 16 |
"hidden_act": "gelu_pytorch_tanh",
|
| 17 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 18 |
+
"hidden_size": 2304,
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 9216,
|
| 21 |
"max_position_embeddings": 8192,
|
| 22 |
"model_type": "gemma2",
|
| 23 |
+
"num_attention_heads": 8,
|
| 24 |
+
"num_hidden_layers": 26,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
"pad_token_id": 0,
|
| 27 |
+
"query_pre_attn_scalar": 256,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"rms_norm_eps": 1e-06,
|
| 29 |
"rope_theta": 10000.0,
|
| 30 |
"sliding_window": 4096,
|
|
|
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.44.2",
|
| 33 |
+
"unsloth_version": "2024.9",
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 256000
|
| 36 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8478b81874947c55cb1349fd181c47ad76b04b2ef7cfec46c6e5b094363a1d5
|
| 3 |
+
size 5228717351
|
model.safetensors.index.json
CHANGED
|
@@ -1,1060 +1,294 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"model.embed_tokens.biases": "model.safetensors",
|
| 7 |
-
"model.embed_tokens.scales": "model.safetensors",
|
| 8 |
"model.embed_tokens.weight": "model.safetensors",
|
| 9 |
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 10 |
-
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 11 |
-
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 12 |
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 13 |
-
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 14 |
-
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 15 |
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 16 |
-
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 17 |
-
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 18 |
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 19 |
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 20 |
"model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
| 21 |
"model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 22 |
-
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 23 |
-
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 24 |
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 25 |
-
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 26 |
-
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 27 |
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 28 |
-
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 29 |
-
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 30 |
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 31 |
-
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 32 |
-
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 33 |
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 34 |
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 35 |
-
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 36 |
-
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 37 |
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 38 |
-
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 39 |
-
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 40 |
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 41 |
-
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 42 |
-
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 43 |
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 44 |
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 45 |
"model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
| 46 |
"model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 47 |
-
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 48 |
-
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 49 |
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 50 |
-
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 51 |
-
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 52 |
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 53 |
-
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 54 |
-
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 55 |
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 56 |
-
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 57 |
-
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 58 |
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 59 |
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 60 |
-
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 61 |
-
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 62 |
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 63 |
-
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 64 |
-
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 65 |
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 66 |
-
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 67 |
-
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 68 |
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 69 |
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 70 |
"model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
| 71 |
"model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 72 |
-
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 73 |
-
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 74 |
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 75 |
-
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 76 |
-
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 77 |
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 78 |
-
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 79 |
-
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 80 |
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 81 |
-
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 82 |
-
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 83 |
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 84 |
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 85 |
-
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 86 |
-
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 87 |
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 88 |
-
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 89 |
-
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 90 |
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 91 |
-
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 92 |
-
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 93 |
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 94 |
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 95 |
"model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
| 96 |
"model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 97 |
-
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 98 |
-
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 99 |
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 100 |
-
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 101 |
-
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 102 |
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 103 |
-
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 104 |
-
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 105 |
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 106 |
-
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 107 |
-
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 108 |
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 109 |
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 110 |
-
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 111 |
-
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 112 |
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 113 |
-
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 114 |
-
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 115 |
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 116 |
-
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 117 |
-
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 118 |
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 119 |
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 120 |
"model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
| 121 |
"model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 122 |
-
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 123 |
-
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 124 |
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 125 |
-
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 126 |
-
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 127 |
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 128 |
-
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 129 |
-
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 130 |
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 131 |
-
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 132 |
-
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 133 |
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 134 |
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 135 |
-
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 136 |
-
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 137 |
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 138 |
-
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 139 |
-
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 140 |
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 141 |
-
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 142 |
-
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 143 |
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 144 |
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 145 |
"model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
| 146 |
"model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 147 |
-
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 148 |
-
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 149 |
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 150 |
-
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 151 |
-
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 152 |
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 153 |
-
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 154 |
-
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 155 |
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 156 |
-
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 157 |
-
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 158 |
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 159 |
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 160 |
-
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 161 |
-
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 162 |
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 163 |
-
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 164 |
-
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 165 |
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 166 |
-
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 167 |
-
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 168 |
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 169 |
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 170 |
"model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
| 171 |
"model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 172 |
-
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 173 |
-
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 174 |
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 175 |
-
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 176 |
-
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 177 |
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 178 |
-
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 179 |
-
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 180 |
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 181 |
-
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 182 |
-
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 183 |
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 184 |
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 185 |
-
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 186 |
-
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 187 |
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 188 |
-
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 189 |
-
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 190 |
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 191 |
-
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 192 |
-
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 193 |
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 194 |
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 195 |
"model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
| 196 |
"model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 197 |
-
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 198 |
-
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 199 |
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 200 |
-
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 201 |
-
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 202 |
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 203 |
-
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 204 |
-
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 205 |
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 206 |
-
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 207 |
-
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 208 |
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 209 |
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 210 |
-
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 211 |
-
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 212 |
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 213 |
-
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 214 |
-
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 215 |
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 216 |
-
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 217 |
-
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 218 |
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 219 |
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 220 |
"model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
| 221 |
"model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 222 |
-
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 223 |
-
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 224 |
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 225 |
-
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 226 |
-
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 227 |
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 228 |
-
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 229 |
-
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 230 |
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 231 |
-
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 232 |
-
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 233 |
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 234 |
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 235 |
-
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 236 |
-
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 237 |
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 238 |
-
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 239 |
-
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 240 |
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 241 |
-
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 242 |
-
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 243 |
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 244 |
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 245 |
"model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
| 246 |
"model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 247 |
-
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 248 |
-
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 249 |
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 250 |
-
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 251 |
-
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 252 |
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 253 |
-
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 254 |
-
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 255 |
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 256 |
-
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 257 |
-
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 258 |
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 259 |
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 260 |
-
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 261 |
-
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 262 |
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 263 |
-
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 264 |
-
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 265 |
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 266 |
-
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 267 |
-
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 268 |
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 269 |
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 270 |
"model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
| 271 |
"model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 272 |
-
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 273 |
-
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 274 |
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 275 |
-
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 276 |
-
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 277 |
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 278 |
-
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 279 |
-
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 280 |
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 281 |
-
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 282 |
-
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 283 |
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 284 |
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 285 |
-
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 286 |
-
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 287 |
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 288 |
-
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 289 |
-
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 290 |
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 291 |
-
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 292 |
-
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 293 |
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 294 |
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 295 |
"model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
| 296 |
"model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 297 |
-
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 298 |
-
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 299 |
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 300 |
-
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 301 |
-
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 302 |
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 303 |
-
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 304 |
-
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 305 |
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 306 |
-
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 307 |
-
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 308 |
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 309 |
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 310 |
-
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 311 |
-
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 312 |
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 313 |
-
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 314 |
-
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 315 |
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 316 |
-
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 317 |
-
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 318 |
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 319 |
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 320 |
"model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
| 321 |
"model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 322 |
-
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 323 |
-
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 324 |
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 325 |
-
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 326 |
-
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 327 |
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 328 |
-
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 329 |
-
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 330 |
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 331 |
-
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 332 |
-
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 333 |
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 334 |
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 335 |
-
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 336 |
-
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 337 |
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 338 |
-
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 339 |
-
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 340 |
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 341 |
-
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 342 |
-
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 343 |
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 344 |
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 345 |
"model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
| 346 |
"model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 347 |
-
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 348 |
-
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 349 |
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 350 |
-
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 351 |
-
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 352 |
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 353 |
-
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 354 |
-
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 355 |
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 356 |
-
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 357 |
-
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 358 |
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 359 |
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 360 |
-
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 361 |
-
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 362 |
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 363 |
-
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 364 |
-
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 365 |
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 366 |
-
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 367 |
-
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 368 |
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 369 |
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 370 |
"model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
| 371 |
"model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 372 |
-
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 373 |
-
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 374 |
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 375 |
-
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 376 |
-
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 377 |
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 378 |
-
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 379 |
-
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 380 |
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 381 |
-
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 382 |
-
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 383 |
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 384 |
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 385 |
-
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 386 |
-
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 387 |
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 388 |
-
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 389 |
-
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 390 |
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 391 |
-
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 392 |
-
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 393 |
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 394 |
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 395 |
"model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
| 396 |
"model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 397 |
-
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 398 |
-
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 399 |
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 400 |
-
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 401 |
-
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 402 |
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 403 |
-
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 404 |
-
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 405 |
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 406 |
-
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 407 |
-
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 408 |
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 409 |
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 410 |
-
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 411 |
-
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 412 |
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 413 |
-
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 414 |
-
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 415 |
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 416 |
-
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 417 |
-
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 418 |
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 419 |
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 420 |
"model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
| 421 |
"model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 422 |
-
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 423 |
-
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 424 |
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 425 |
-
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 426 |
-
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 427 |
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 428 |
-
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 429 |
-
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 430 |
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 431 |
-
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 432 |
-
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 433 |
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 434 |
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 435 |
-
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 436 |
-
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 437 |
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 438 |
-
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 439 |
-
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 440 |
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 441 |
-
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 442 |
-
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 443 |
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 444 |
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 445 |
"model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
| 446 |
"model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 447 |
-
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 448 |
-
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 449 |
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 450 |
-
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 451 |
-
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 452 |
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 453 |
-
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 454 |
-
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 455 |
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 456 |
-
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 457 |
-
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 458 |
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 459 |
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 460 |
-
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 461 |
-
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 462 |
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 463 |
-
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 464 |
-
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 465 |
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 466 |
-
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 467 |
-
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 468 |
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 469 |
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 470 |
"model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
| 471 |
"model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 472 |
-
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 473 |
-
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 474 |
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 475 |
-
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 476 |
-
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 477 |
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 478 |
-
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 479 |
-
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 480 |
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 481 |
-
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 482 |
-
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 483 |
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 484 |
-
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 485 |
-
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 486 |
-
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 487 |
-
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 488 |
-
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 489 |
-
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 490 |
-
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 491 |
-
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 492 |
-
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 493 |
-
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 494 |
-
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 495 |
-
"model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
|
| 496 |
-
"model.layers.26.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 497 |
-
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 498 |
-
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 499 |
-
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 500 |
-
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 501 |
-
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 502 |
-
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 503 |
-
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 504 |
-
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 505 |
-
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 506 |
-
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 507 |
-
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 508 |
-
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 509 |
-
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 510 |
-
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 511 |
-
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 512 |
-
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 513 |
-
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 514 |
-
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 515 |
-
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 516 |
-
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 517 |
-
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 518 |
-
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 519 |
-
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 520 |
-
"model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
|
| 521 |
-
"model.layers.27.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 522 |
-
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 523 |
-
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 524 |
-
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 525 |
-
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 526 |
-
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 527 |
-
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 528 |
-
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 529 |
-
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 530 |
-
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 531 |
-
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 532 |
-
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 533 |
-
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 534 |
-
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 535 |
-
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 536 |
-
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 537 |
-
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 538 |
-
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 539 |
-
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 540 |
-
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 541 |
-
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 542 |
-
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 543 |
-
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 544 |
-
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 545 |
-
"model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
|
| 546 |
-
"model.layers.28.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 547 |
-
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 548 |
-
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 549 |
-
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 550 |
-
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 551 |
-
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 552 |
-
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 553 |
-
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 554 |
-
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 555 |
-
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 556 |
-
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 557 |
-
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 558 |
-
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 559 |
-
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 560 |
-
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 561 |
-
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 562 |
-
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 563 |
-
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 564 |
-
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 565 |
-
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 566 |
-
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 567 |
-
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 568 |
-
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 569 |
-
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 570 |
-
"model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
|
| 571 |
-
"model.layers.29.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 572 |
-
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 573 |
-
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 574 |
-
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 575 |
-
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 576 |
-
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 577 |
-
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 578 |
-
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 579 |
-
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 580 |
-
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 581 |
-
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 582 |
-
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 583 |
-
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 584 |
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 585 |
-
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 586 |
-
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 587 |
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 588 |
-
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 589 |
-
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 590 |
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 591 |
-
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 592 |
-
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 593 |
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 594 |
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 595 |
"model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
| 596 |
"model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 597 |
-
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 598 |
-
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 599 |
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 600 |
-
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 601 |
-
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 602 |
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 603 |
-
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 604 |
-
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 605 |
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 606 |
-
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 607 |
-
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 608 |
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 609 |
-
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 610 |
-
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 611 |
-
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 612 |
-
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 613 |
-
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 614 |
-
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 615 |
-
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 616 |
-
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 617 |
-
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 618 |
-
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 619 |
-
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 620 |
-
"model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
|
| 621 |
-
"model.layers.30.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 622 |
-
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 623 |
-
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 624 |
-
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 625 |
-
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 626 |
-
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 627 |
-
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 628 |
-
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 629 |
-
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 630 |
-
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 631 |
-
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 632 |
-
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 633 |
-
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 634 |
-
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 635 |
-
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 636 |
-
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 637 |
-
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 638 |
-
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 639 |
-
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 640 |
-
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 641 |
-
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 642 |
-
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 643 |
-
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 644 |
-
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 645 |
-
"model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
|
| 646 |
-
"model.layers.31.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 647 |
-
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 648 |
-
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 649 |
-
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 650 |
-
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 651 |
-
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 652 |
-
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 653 |
-
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 654 |
-
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 655 |
-
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 656 |
-
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 657 |
-
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 658 |
-
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 659 |
-
"model.layers.32.input_layernorm.weight": "model.safetensors",
|
| 660 |
-
"model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 661 |
-
"model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 662 |
-
"model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 663 |
-
"model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 664 |
-
"model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 665 |
-
"model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 666 |
-
"model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 667 |
-
"model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 668 |
-
"model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 669 |
-
"model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 670 |
-
"model.layers.32.post_feedforward_layernorm.weight": "model.safetensors",
|
| 671 |
-
"model.layers.32.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 672 |
-
"model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 673 |
-
"model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 674 |
-
"model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 675 |
-
"model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 676 |
-
"model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 677 |
-
"model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 678 |
-
"model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 679 |
-
"model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 680 |
-
"model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 681 |
-
"model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 682 |
-
"model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 683 |
-
"model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 684 |
-
"model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 685 |
-
"model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 686 |
-
"model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 687 |
-
"model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 688 |
-
"model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 689 |
-
"model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 690 |
-
"model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 691 |
-
"model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 692 |
-
"model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 693 |
-
"model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 694 |
-
"model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 695 |
-
"model.layers.33.post_feedforward_layernorm.weight": "model.safetensors",
|
| 696 |
-
"model.layers.33.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 697 |
-
"model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 698 |
-
"model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 699 |
-
"model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 700 |
-
"model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 701 |
-
"model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 702 |
-
"model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 703 |
-
"model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 704 |
-
"model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 705 |
-
"model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 706 |
-
"model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 707 |
-
"model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 708 |
-
"model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 709 |
-
"model.layers.34.input_layernorm.weight": "model.safetensors",
|
| 710 |
-
"model.layers.34.mlp.down_proj.biases": "model.safetensors",
|
| 711 |
-
"model.layers.34.mlp.down_proj.scales": "model.safetensors",
|
| 712 |
-
"model.layers.34.mlp.down_proj.weight": "model.safetensors",
|
| 713 |
-
"model.layers.34.mlp.gate_proj.biases": "model.safetensors",
|
| 714 |
-
"model.layers.34.mlp.gate_proj.scales": "model.safetensors",
|
| 715 |
-
"model.layers.34.mlp.gate_proj.weight": "model.safetensors",
|
| 716 |
-
"model.layers.34.mlp.up_proj.biases": "model.safetensors",
|
| 717 |
-
"model.layers.34.mlp.up_proj.scales": "model.safetensors",
|
| 718 |
-
"model.layers.34.mlp.up_proj.weight": "model.safetensors",
|
| 719 |
-
"model.layers.34.post_attention_layernorm.weight": "model.safetensors",
|
| 720 |
-
"model.layers.34.post_feedforward_layernorm.weight": "model.safetensors",
|
| 721 |
-
"model.layers.34.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 722 |
-
"model.layers.34.self_attn.k_proj.biases": "model.safetensors",
|
| 723 |
-
"model.layers.34.self_attn.k_proj.scales": "model.safetensors",
|
| 724 |
-
"model.layers.34.self_attn.k_proj.weight": "model.safetensors",
|
| 725 |
-
"model.layers.34.self_attn.o_proj.biases": "model.safetensors",
|
| 726 |
-
"model.layers.34.self_attn.o_proj.scales": "model.safetensors",
|
| 727 |
-
"model.layers.34.self_attn.o_proj.weight": "model.safetensors",
|
| 728 |
-
"model.layers.34.self_attn.q_proj.biases": "model.safetensors",
|
| 729 |
-
"model.layers.34.self_attn.q_proj.scales": "model.safetensors",
|
| 730 |
-
"model.layers.34.self_attn.q_proj.weight": "model.safetensors",
|
| 731 |
-
"model.layers.34.self_attn.v_proj.biases": "model.safetensors",
|
| 732 |
-
"model.layers.34.self_attn.v_proj.scales": "model.safetensors",
|
| 733 |
-
"model.layers.34.self_attn.v_proj.weight": "model.safetensors",
|
| 734 |
-
"model.layers.35.input_layernorm.weight": "model.safetensors",
|
| 735 |
-
"model.layers.35.mlp.down_proj.biases": "model.safetensors",
|
| 736 |
-
"model.layers.35.mlp.down_proj.scales": "model.safetensors",
|
| 737 |
-
"model.layers.35.mlp.down_proj.weight": "model.safetensors",
|
| 738 |
-
"model.layers.35.mlp.gate_proj.biases": "model.safetensors",
|
| 739 |
-
"model.layers.35.mlp.gate_proj.scales": "model.safetensors",
|
| 740 |
-
"model.layers.35.mlp.gate_proj.weight": "model.safetensors",
|
| 741 |
-
"model.layers.35.mlp.up_proj.biases": "model.safetensors",
|
| 742 |
-
"model.layers.35.mlp.up_proj.scales": "model.safetensors",
|
| 743 |
-
"model.layers.35.mlp.up_proj.weight": "model.safetensors",
|
| 744 |
-
"model.layers.35.post_attention_layernorm.weight": "model.safetensors",
|
| 745 |
-
"model.layers.35.post_feedforward_layernorm.weight": "model.safetensors",
|
| 746 |
-
"model.layers.35.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 747 |
-
"model.layers.35.self_attn.k_proj.biases": "model.safetensors",
|
| 748 |
-
"model.layers.35.self_attn.k_proj.scales": "model.safetensors",
|
| 749 |
-
"model.layers.35.self_attn.k_proj.weight": "model.safetensors",
|
| 750 |
-
"model.layers.35.self_attn.o_proj.biases": "model.safetensors",
|
| 751 |
-
"model.layers.35.self_attn.o_proj.scales": "model.safetensors",
|
| 752 |
-
"model.layers.35.self_attn.o_proj.weight": "model.safetensors",
|
| 753 |
-
"model.layers.35.self_attn.q_proj.biases": "model.safetensors",
|
| 754 |
-
"model.layers.35.self_attn.q_proj.scales": "model.safetensors",
|
| 755 |
-
"model.layers.35.self_attn.q_proj.weight": "model.safetensors",
|
| 756 |
-
"model.layers.35.self_attn.v_proj.biases": "model.safetensors",
|
| 757 |
-
"model.layers.35.self_attn.v_proj.scales": "model.safetensors",
|
| 758 |
-
"model.layers.35.self_attn.v_proj.weight": "model.safetensors",
|
| 759 |
-
"model.layers.36.input_layernorm.weight": "model.safetensors",
|
| 760 |
-
"model.layers.36.mlp.down_proj.biases": "model.safetensors",
|
| 761 |
-
"model.layers.36.mlp.down_proj.scales": "model.safetensors",
|
| 762 |
-
"model.layers.36.mlp.down_proj.weight": "model.safetensors",
|
| 763 |
-
"model.layers.36.mlp.gate_proj.biases": "model.safetensors",
|
| 764 |
-
"model.layers.36.mlp.gate_proj.scales": "model.safetensors",
|
| 765 |
-
"model.layers.36.mlp.gate_proj.weight": "model.safetensors",
|
| 766 |
-
"model.layers.36.mlp.up_proj.biases": "model.safetensors",
|
| 767 |
-
"model.layers.36.mlp.up_proj.scales": "model.safetensors",
|
| 768 |
-
"model.layers.36.mlp.up_proj.weight": "model.safetensors",
|
| 769 |
-
"model.layers.36.post_attention_layernorm.weight": "model.safetensors",
|
| 770 |
-
"model.layers.36.post_feedforward_layernorm.weight": "model.safetensors",
|
| 771 |
-
"model.layers.36.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 772 |
-
"model.layers.36.self_attn.k_proj.biases": "model.safetensors",
|
| 773 |
-
"model.layers.36.self_attn.k_proj.scales": "model.safetensors",
|
| 774 |
-
"model.layers.36.self_attn.k_proj.weight": "model.safetensors",
|
| 775 |
-
"model.layers.36.self_attn.o_proj.biases": "model.safetensors",
|
| 776 |
-
"model.layers.36.self_attn.o_proj.scales": "model.safetensors",
|
| 777 |
-
"model.layers.36.self_attn.o_proj.weight": "model.safetensors",
|
| 778 |
-
"model.layers.36.self_attn.q_proj.biases": "model.safetensors",
|
| 779 |
-
"model.layers.36.self_attn.q_proj.scales": "model.safetensors",
|
| 780 |
-
"model.layers.36.self_attn.q_proj.weight": "model.safetensors",
|
| 781 |
-
"model.layers.36.self_attn.v_proj.biases": "model.safetensors",
|
| 782 |
-
"model.layers.36.self_attn.v_proj.scales": "model.safetensors",
|
| 783 |
-
"model.layers.36.self_attn.v_proj.weight": "model.safetensors",
|
| 784 |
-
"model.layers.37.input_layernorm.weight": "model.safetensors",
|
| 785 |
-
"model.layers.37.mlp.down_proj.biases": "model.safetensors",
|
| 786 |
-
"model.layers.37.mlp.down_proj.scales": "model.safetensors",
|
| 787 |
-
"model.layers.37.mlp.down_proj.weight": "model.safetensors",
|
| 788 |
-
"model.layers.37.mlp.gate_proj.biases": "model.safetensors",
|
| 789 |
-
"model.layers.37.mlp.gate_proj.scales": "model.safetensors",
|
| 790 |
-
"model.layers.37.mlp.gate_proj.weight": "model.safetensors",
|
| 791 |
-
"model.layers.37.mlp.up_proj.biases": "model.safetensors",
|
| 792 |
-
"model.layers.37.mlp.up_proj.scales": "model.safetensors",
|
| 793 |
-
"model.layers.37.mlp.up_proj.weight": "model.safetensors",
|
| 794 |
-
"model.layers.37.post_attention_layernorm.weight": "model.safetensors",
|
| 795 |
-
"model.layers.37.post_feedforward_layernorm.weight": "model.safetensors",
|
| 796 |
-
"model.layers.37.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 797 |
-
"model.layers.37.self_attn.k_proj.biases": "model.safetensors",
|
| 798 |
-
"model.layers.37.self_attn.k_proj.scales": "model.safetensors",
|
| 799 |
-
"model.layers.37.self_attn.k_proj.weight": "model.safetensors",
|
| 800 |
-
"model.layers.37.self_attn.o_proj.biases": "model.safetensors",
|
| 801 |
-
"model.layers.37.self_attn.o_proj.scales": "model.safetensors",
|
| 802 |
-
"model.layers.37.self_attn.o_proj.weight": "model.safetensors",
|
| 803 |
-
"model.layers.37.self_attn.q_proj.biases": "model.safetensors",
|
| 804 |
-
"model.layers.37.self_attn.q_proj.scales": "model.safetensors",
|
| 805 |
-
"model.layers.37.self_attn.q_proj.weight": "model.safetensors",
|
| 806 |
-
"model.layers.37.self_attn.v_proj.biases": "model.safetensors",
|
| 807 |
-
"model.layers.37.self_attn.v_proj.scales": "model.safetensors",
|
| 808 |
-
"model.layers.37.self_attn.v_proj.weight": "model.safetensors",
|
| 809 |
-
"model.layers.38.input_layernorm.weight": "model.safetensors",
|
| 810 |
-
"model.layers.38.mlp.down_proj.biases": "model.safetensors",
|
| 811 |
-
"model.layers.38.mlp.down_proj.scales": "model.safetensors",
|
| 812 |
-
"model.layers.38.mlp.down_proj.weight": "model.safetensors",
|
| 813 |
-
"model.layers.38.mlp.gate_proj.biases": "model.safetensors",
|
| 814 |
-
"model.layers.38.mlp.gate_proj.scales": "model.safetensors",
|
| 815 |
-
"model.layers.38.mlp.gate_proj.weight": "model.safetensors",
|
| 816 |
-
"model.layers.38.mlp.up_proj.biases": "model.safetensors",
|
| 817 |
-
"model.layers.38.mlp.up_proj.scales": "model.safetensors",
|
| 818 |
-
"model.layers.38.mlp.up_proj.weight": "model.safetensors",
|
| 819 |
-
"model.layers.38.post_attention_layernorm.weight": "model.safetensors",
|
| 820 |
-
"model.layers.38.post_feedforward_layernorm.weight": "model.safetensors",
|
| 821 |
-
"model.layers.38.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 822 |
-
"model.layers.38.self_attn.k_proj.biases": "model.safetensors",
|
| 823 |
-
"model.layers.38.self_attn.k_proj.scales": "model.safetensors",
|
| 824 |
-
"model.layers.38.self_attn.k_proj.weight": "model.safetensors",
|
| 825 |
-
"model.layers.38.self_attn.o_proj.biases": "model.safetensors",
|
| 826 |
-
"model.layers.38.self_attn.o_proj.scales": "model.safetensors",
|
| 827 |
-
"model.layers.38.self_attn.o_proj.weight": "model.safetensors",
|
| 828 |
-
"model.layers.38.self_attn.q_proj.biases": "model.safetensors",
|
| 829 |
-
"model.layers.38.self_attn.q_proj.scales": "model.safetensors",
|
| 830 |
-
"model.layers.38.self_attn.q_proj.weight": "model.safetensors",
|
| 831 |
-
"model.layers.38.self_attn.v_proj.biases": "model.safetensors",
|
| 832 |
-
"model.layers.38.self_attn.v_proj.scales": "model.safetensors",
|
| 833 |
-
"model.layers.38.self_attn.v_proj.weight": "model.safetensors",
|
| 834 |
-
"model.layers.39.input_layernorm.weight": "model.safetensors",
|
| 835 |
-
"model.layers.39.mlp.down_proj.biases": "model.safetensors",
|
| 836 |
-
"model.layers.39.mlp.down_proj.scales": "model.safetensors",
|
| 837 |
-
"model.layers.39.mlp.down_proj.weight": "model.safetensors",
|
| 838 |
-
"model.layers.39.mlp.gate_proj.biases": "model.safetensors",
|
| 839 |
-
"model.layers.39.mlp.gate_proj.scales": "model.safetensors",
|
| 840 |
-
"model.layers.39.mlp.gate_proj.weight": "model.safetensors",
|
| 841 |
-
"model.layers.39.mlp.up_proj.biases": "model.safetensors",
|
| 842 |
-
"model.layers.39.mlp.up_proj.scales": "model.safetensors",
|
| 843 |
-
"model.layers.39.mlp.up_proj.weight": "model.safetensors",
|
| 844 |
-
"model.layers.39.post_attention_layernorm.weight": "model.safetensors",
|
| 845 |
-
"model.layers.39.post_feedforward_layernorm.weight": "model.safetensors",
|
| 846 |
-
"model.layers.39.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 847 |
-
"model.layers.39.self_attn.k_proj.biases": "model.safetensors",
|
| 848 |
-
"model.layers.39.self_attn.k_proj.scales": "model.safetensors",
|
| 849 |
-
"model.layers.39.self_attn.k_proj.weight": "model.safetensors",
|
| 850 |
-
"model.layers.39.self_attn.o_proj.biases": "model.safetensors",
|
| 851 |
-
"model.layers.39.self_attn.o_proj.scales": "model.safetensors",
|
| 852 |
-
"model.layers.39.self_attn.o_proj.weight": "model.safetensors",
|
| 853 |
-
"model.layers.39.self_attn.q_proj.biases": "model.safetensors",
|
| 854 |
-
"model.layers.39.self_attn.q_proj.scales": "model.safetensors",
|
| 855 |
-
"model.layers.39.self_attn.q_proj.weight": "model.safetensors",
|
| 856 |
-
"model.layers.39.self_attn.v_proj.biases": "model.safetensors",
|
| 857 |
-
"model.layers.39.self_attn.v_proj.scales": "model.safetensors",
|
| 858 |
-
"model.layers.39.self_attn.v_proj.weight": "model.safetensors",
|
| 859 |
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 860 |
-
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 861 |
-
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 862 |
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 863 |
-
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 864 |
-
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 865 |
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 866 |
-
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 867 |
-
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 868 |
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 869 |
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 870 |
"model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
| 871 |
"model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 872 |
-
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 873 |
-
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 874 |
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 875 |
-
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 876 |
-
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 877 |
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 878 |
-
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 879 |
-
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 880 |
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 881 |
-
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 882 |
-
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 883 |
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 884 |
-
"model.layers.40.input_layernorm.weight": "model.safetensors",
|
| 885 |
-
"model.layers.40.mlp.down_proj.biases": "model.safetensors",
|
| 886 |
-
"model.layers.40.mlp.down_proj.scales": "model.safetensors",
|
| 887 |
-
"model.layers.40.mlp.down_proj.weight": "model.safetensors",
|
| 888 |
-
"model.layers.40.mlp.gate_proj.biases": "model.safetensors",
|
| 889 |
-
"model.layers.40.mlp.gate_proj.scales": "model.safetensors",
|
| 890 |
-
"model.layers.40.mlp.gate_proj.weight": "model.safetensors",
|
| 891 |
-
"model.layers.40.mlp.up_proj.biases": "model.safetensors",
|
| 892 |
-
"model.layers.40.mlp.up_proj.scales": "model.safetensors",
|
| 893 |
-
"model.layers.40.mlp.up_proj.weight": "model.safetensors",
|
| 894 |
-
"model.layers.40.post_attention_layernorm.weight": "model.safetensors",
|
| 895 |
-
"model.layers.40.post_feedforward_layernorm.weight": "model.safetensors",
|
| 896 |
-
"model.layers.40.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 897 |
-
"model.layers.40.self_attn.k_proj.biases": "model.safetensors",
|
| 898 |
-
"model.layers.40.self_attn.k_proj.scales": "model.safetensors",
|
| 899 |
-
"model.layers.40.self_attn.k_proj.weight": "model.safetensors",
|
| 900 |
-
"model.layers.40.self_attn.o_proj.biases": "model.safetensors",
|
| 901 |
-
"model.layers.40.self_attn.o_proj.scales": "model.safetensors",
|
| 902 |
-
"model.layers.40.self_attn.o_proj.weight": "model.safetensors",
|
| 903 |
-
"model.layers.40.self_attn.q_proj.biases": "model.safetensors",
|
| 904 |
-
"model.layers.40.self_attn.q_proj.scales": "model.safetensors",
|
| 905 |
-
"model.layers.40.self_attn.q_proj.weight": "model.safetensors",
|
| 906 |
-
"model.layers.40.self_attn.v_proj.biases": "model.safetensors",
|
| 907 |
-
"model.layers.40.self_attn.v_proj.scales": "model.safetensors",
|
| 908 |
-
"model.layers.40.self_attn.v_proj.weight": "model.safetensors",
|
| 909 |
-
"model.layers.41.input_layernorm.weight": "model.safetensors",
|
| 910 |
-
"model.layers.41.mlp.down_proj.biases": "model.safetensors",
|
| 911 |
-
"model.layers.41.mlp.down_proj.scales": "model.safetensors",
|
| 912 |
-
"model.layers.41.mlp.down_proj.weight": "model.safetensors",
|
| 913 |
-
"model.layers.41.mlp.gate_proj.biases": "model.safetensors",
|
| 914 |
-
"model.layers.41.mlp.gate_proj.scales": "model.safetensors",
|
| 915 |
-
"model.layers.41.mlp.gate_proj.weight": "model.safetensors",
|
| 916 |
-
"model.layers.41.mlp.up_proj.biases": "model.safetensors",
|
| 917 |
-
"model.layers.41.mlp.up_proj.scales": "model.safetensors",
|
| 918 |
-
"model.layers.41.mlp.up_proj.weight": "model.safetensors",
|
| 919 |
-
"model.layers.41.post_attention_layernorm.weight": "model.safetensors",
|
| 920 |
-
"model.layers.41.post_feedforward_layernorm.weight": "model.safetensors",
|
| 921 |
-
"model.layers.41.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 922 |
-
"model.layers.41.self_attn.k_proj.biases": "model.safetensors",
|
| 923 |
-
"model.layers.41.self_attn.k_proj.scales": "model.safetensors",
|
| 924 |
-
"model.layers.41.self_attn.k_proj.weight": "model.safetensors",
|
| 925 |
-
"model.layers.41.self_attn.o_proj.biases": "model.safetensors",
|
| 926 |
-
"model.layers.41.self_attn.o_proj.scales": "model.safetensors",
|
| 927 |
-
"model.layers.41.self_attn.o_proj.weight": "model.safetensors",
|
| 928 |
-
"model.layers.41.self_attn.q_proj.biases": "model.safetensors",
|
| 929 |
-
"model.layers.41.self_attn.q_proj.scales": "model.safetensors",
|
| 930 |
-
"model.layers.41.self_attn.q_proj.weight": "model.safetensors",
|
| 931 |
-
"model.layers.41.self_attn.v_proj.biases": "model.safetensors",
|
| 932 |
-
"model.layers.41.self_attn.v_proj.scales": "model.safetensors",
|
| 933 |
-
"model.layers.41.self_attn.v_proj.weight": "model.safetensors",
|
| 934 |
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 935 |
-
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 936 |
-
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 937 |
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 938 |
-
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 939 |
-
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 940 |
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 941 |
-
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 942 |
-
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 943 |
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 944 |
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 945 |
"model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
| 946 |
"model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 947 |
-
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 948 |
-
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 949 |
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 950 |
-
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 951 |
-
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 952 |
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 953 |
-
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 954 |
-
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 955 |
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 956 |
-
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 957 |
-
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 958 |
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 959 |
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 960 |
-
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 961 |
-
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 962 |
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 963 |
-
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 964 |
-
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 965 |
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 966 |
-
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 967 |
-
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 968 |
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 969 |
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 970 |
"model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
| 971 |
"model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 972 |
-
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 973 |
-
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 974 |
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 975 |
-
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 976 |
-
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 977 |
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 978 |
-
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 979 |
-
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 980 |
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 981 |
-
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 982 |
-
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 983 |
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 984 |
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 985 |
-
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 986 |
-
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 987 |
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 988 |
-
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 989 |
-
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 990 |
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 991 |
-
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 992 |
-
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 993 |
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 994 |
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 995 |
"model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
| 996 |
"model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 997 |
-
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 998 |
-
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 999 |
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 1000 |
-
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 1001 |
-
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 1002 |
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 1003 |
-
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 1004 |
-
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 1005 |
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 1006 |
-
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 1007 |
-
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 1008 |
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 1009 |
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 1010 |
-
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 1011 |
-
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 1012 |
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 1013 |
-
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 1014 |
-
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 1015 |
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 1016 |
-
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 1017 |
-
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 1018 |
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 1019 |
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 1020 |
"model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1021 |
"model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1022 |
-
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 1023 |
-
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 1024 |
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 1025 |
-
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 1026 |
-
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 1027 |
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 1028 |
-
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 1029 |
-
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 1030 |
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 1031 |
-
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 1032 |
-
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 1033 |
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 1034 |
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 1035 |
-
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 1036 |
-
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 1037 |
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 1038 |
-
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 1039 |
-
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 1040 |
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 1041 |
-
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 1042 |
-
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 1043 |
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 1044 |
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 1045 |
"model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1046 |
"model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1047 |
-
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 1048 |
-
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 1049 |
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 1050 |
-
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 1051 |
-
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 1052 |
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 1053 |
-
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 1054 |
-
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 1055 |
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 1056 |
-
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 1057 |
-
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 1058 |
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 1059 |
"model.norm.weight": "model.safetensors"
|
| 1060 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 5228683776
|
| 4 |
},
|
| 5 |
"weight_map": {
|
|
|
|
|
|
|
| 6 |
"model.embed_tokens.weight": "model.safetensors",
|
| 7 |
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 8 |
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 9 |
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 10 |
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 11 |
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 12 |
"model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
| 13 |
"model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 14 |
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 15 |
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 16 |
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 17 |
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 18 |
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 19 |
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 20 |
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 21 |
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 22 |
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 23 |
"model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
| 24 |
"model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 25 |
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 26 |
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 27 |
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 28 |
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 29 |
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 30 |
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 31 |
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 32 |
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 33 |
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 34 |
"model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
| 35 |
"model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 36 |
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 37 |
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 38 |
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 39 |
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 40 |
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 41 |
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 42 |
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 43 |
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 44 |
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 45 |
"model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
| 46 |
"model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 47 |
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 48 |
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 49 |
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 50 |
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 51 |
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 52 |
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 53 |
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 54 |
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 55 |
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 56 |
"model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
| 57 |
"model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 58 |
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 59 |
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 60 |
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 61 |
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 62 |
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 63 |
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 64 |
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 65 |
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 66 |
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 67 |
"model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
| 68 |
"model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 69 |
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 70 |
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 71 |
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 72 |
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 73 |
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 74 |
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 75 |
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 76 |
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 77 |
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 78 |
"model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
| 79 |
"model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 80 |
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 81 |
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 82 |
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 83 |
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 84 |
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 85 |
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 86 |
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 87 |
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 88 |
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 89 |
"model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
| 90 |
"model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 91 |
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 92 |
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 93 |
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 94 |
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 95 |
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 96 |
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 97 |
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 98 |
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 99 |
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 100 |
"model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
| 101 |
"model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 102 |
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 103 |
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 104 |
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 105 |
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 106 |
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 107 |
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 108 |
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 109 |
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 110 |
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 111 |
"model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
| 112 |
"model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 113 |
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 114 |
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 115 |
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 116 |
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 117 |
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 118 |
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 119 |
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 120 |
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 121 |
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 122 |
"model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
| 123 |
"model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 124 |
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 125 |
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 126 |
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 127 |
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 128 |
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 129 |
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 130 |
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 131 |
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 132 |
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 133 |
"model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
| 134 |
"model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 135 |
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 136 |
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 137 |
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 138 |
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 139 |
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 140 |
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 141 |
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 142 |
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 143 |
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 144 |
"model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
| 145 |
"model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 146 |
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 147 |
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 148 |
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 149 |
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 150 |
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 151 |
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 152 |
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 153 |
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 154 |
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 155 |
"model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
| 156 |
"model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 157 |
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 158 |
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 159 |
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 160 |
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 161 |
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 162 |
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 163 |
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 164 |
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 165 |
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 166 |
"model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
| 167 |
"model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 168 |
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 169 |
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 170 |
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 171 |
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 172 |
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 173 |
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 174 |
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 175 |
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 176 |
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 177 |
"model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
| 178 |
"model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 179 |
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 180 |
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 181 |
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 182 |
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 183 |
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 184 |
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 185 |
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 186 |
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 187 |
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 188 |
"model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
| 189 |
"model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 190 |
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 191 |
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 192 |
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 193 |
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 194 |
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 195 |
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 196 |
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 197 |
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 198 |
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 199 |
"model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
| 200 |
"model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 201 |
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 202 |
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 203 |
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 204 |
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 205 |
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 206 |
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 207 |
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 208 |
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 209 |
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 210 |
"model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
| 211 |
"model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 212 |
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 213 |
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 214 |
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 215 |
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 217 |
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 218 |
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 219 |
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 220 |
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 221 |
"model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
| 222 |
"model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 223 |
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 224 |
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 225 |
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 226 |
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 228 |
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 229 |
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 230 |
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 231 |
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 232 |
"model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
| 233 |
"model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 234 |
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 235 |
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 236 |
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 237 |
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 239 |
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 240 |
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 241 |
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 242 |
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 243 |
"model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
| 244 |
"model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 245 |
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 246 |
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 247 |
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 248 |
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 249 |
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 250 |
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 251 |
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 252 |
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 253 |
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 254 |
"model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
| 255 |
"model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 256 |
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 257 |
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 258 |
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 259 |
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 260 |
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 261 |
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 262 |
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 263 |
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 264 |
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 265 |
"model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
| 266 |
"model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 267 |
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 268 |
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 269 |
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 270 |
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 271 |
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 272 |
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 273 |
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 274 |
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 275 |
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 276 |
"model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
| 277 |
"model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 278 |
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 279 |
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 280 |
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 281 |
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 282 |
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 283 |
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 284 |
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 285 |
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 286 |
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 287 |
"model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
| 288 |
"model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
|
|
|
|
|
|
|
| 289 |
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 290 |
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 291 |
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
|
|
|
|
|
|
| 292 |
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 293 |
"model.norm.weight": "model.safetensors"
|
| 294 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
|
| 3 |
+
size 34362873
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
|
@@ -1737,6 +1737,262 @@
|
|
| 1737 |
"rstrip": false,
|
| 1738 |
"single_word": false,
|
| 1739 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1740 |
}
|
| 1741 |
},
|
| 1742 |
"additional_special_tokens": [
|
|
@@ -1749,6 +2005,7 @@
|
|
| 1749 |
"eos_token": "<eos>",
|
| 1750 |
"model_max_length": 1000000000000000019884624838656,
|
| 1751 |
"pad_token": "<pad>",
|
|
|
|
| 1752 |
"sp_model_kwargs": {},
|
| 1753 |
"spaces_between_special_tokens": false,
|
| 1754 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
|
|
|
| 1737 |
"rstrip": false,
|
| 1738 |
"single_word": false,
|
| 1739 |
"special": false
|
| 1740 |
+
},
|
| 1741 |
+
"255968": {
|
| 1742 |
+
"content": "[toxicity=0]",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": false
|
| 1748 |
+
},
|
| 1749 |
+
"255969": {
|
| 1750 |
+
"content": "\t\t",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": false
|
| 1756 |
+
},
|
| 1757 |
+
"255970": {
|
| 1758 |
+
"content": "\t\t\t",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": false
|
| 1764 |
+
},
|
| 1765 |
+
"255971": {
|
| 1766 |
+
"content": "\t\t\t\t",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": false
|
| 1772 |
+
},
|
| 1773 |
+
"255972": {
|
| 1774 |
+
"content": "\t\t\t\t\t",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": false
|
| 1780 |
+
},
|
| 1781 |
+
"255973": {
|
| 1782 |
+
"content": "\t\t\t\t\t\t",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": false
|
| 1788 |
+
},
|
| 1789 |
+
"255974": {
|
| 1790 |
+
"content": "\t\t\t\t\t\t\t",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": false
|
| 1796 |
+
},
|
| 1797 |
+
"255975": {
|
| 1798 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": false
|
| 1804 |
+
},
|
| 1805 |
+
"255976": {
|
| 1806 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": false
|
| 1812 |
+
},
|
| 1813 |
+
"255977": {
|
| 1814 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": false
|
| 1820 |
+
},
|
| 1821 |
+
"255978": {
|
| 1822 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": false
|
| 1828 |
+
},
|
| 1829 |
+
"255979": {
|
| 1830 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": false
|
| 1836 |
+
},
|
| 1837 |
+
"255980": {
|
| 1838 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": false
|
| 1844 |
+
},
|
| 1845 |
+
"255981": {
|
| 1846 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": false
|
| 1852 |
+
},
|
| 1853 |
+
"255982": {
|
| 1854 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": false
|
| 1860 |
+
},
|
| 1861 |
+
"255983": {
|
| 1862 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": false
|
| 1868 |
+
},
|
| 1869 |
+
"255984": {
|
| 1870 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": false
|
| 1876 |
+
},
|
| 1877 |
+
"255985": {
|
| 1878 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": false
|
| 1884 |
+
},
|
| 1885 |
+
"255986": {
|
| 1886 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": false
|
| 1892 |
+
},
|
| 1893 |
+
"255987": {
|
| 1894 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": false
|
| 1900 |
+
},
|
| 1901 |
+
"255988": {
|
| 1902 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": false
|
| 1908 |
+
},
|
| 1909 |
+
"255989": {
|
| 1910 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": false
|
| 1916 |
+
},
|
| 1917 |
+
"255990": {
|
| 1918 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": false
|
| 1924 |
+
},
|
| 1925 |
+
"255991": {
|
| 1926 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": false
|
| 1932 |
+
},
|
| 1933 |
+
"255992": {
|
| 1934 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": false
|
| 1940 |
+
},
|
| 1941 |
+
"255993": {
|
| 1942 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": false
|
| 1948 |
+
},
|
| 1949 |
+
"255994": {
|
| 1950 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": false
|
| 1956 |
+
},
|
| 1957 |
+
"255995": {
|
| 1958 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": false
|
| 1964 |
+
},
|
| 1965 |
+
"255996": {
|
| 1966 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": false
|
| 1972 |
+
},
|
| 1973 |
+
"255997": {
|
| 1974 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": false
|
| 1980 |
+
},
|
| 1981 |
+
"255998": {
|
| 1982 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": false
|
| 1988 |
+
},
|
| 1989 |
+
"255999": {
|
| 1990 |
+
"content": "<unused99>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": false
|
| 1996 |
}
|
| 1997 |
},
|
| 1998 |
"additional_special_tokens": [
|
|
|
|
| 2005 |
"eos_token": "<eos>",
|
| 2006 |
"model_max_length": 1000000000000000019884624838656,
|
| 2007 |
"pad_token": "<pad>",
|
| 2008 |
+
"padding_side": "left",
|
| 2009 |
"sp_model_kwargs": {},
|
| 2010 |
"spaces_between_special_tokens": false,
|
| 2011 |
"tokenizer_class": "GemmaTokenizer",
|