Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# MiS-Firefly-v0.2-22B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /mnt/models/checkpoint-404
+* /mnt/models/checkpoint-808
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+models:
+  - model: /mnt/models/checkpoint-808
+  - model: /mnt/models/checkpoint-404
+merge_method: slerp
+base_model: /mnt/models/checkpoint-808
+parameters:
+  t:
+    - value: [0, 0, 0.25, 0.35, 0.4, 0.45, 0.4, 0.35, 0.25, 0, 0]
+  embed_slerp: true
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "invisietch/MiS-Firefly-v0.2-22B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+dtype: bfloat16
+models:
+  - model: /mnt/models/MiS-Firefly-v0.1-22B
+  - model: /mnt/models/fireflyepoch1
+merge_method: slerp
+base_model: /mnt/models/MiS-Firefly-v0.1-22B
+parameters:
+  t:
+    - value: [0, 0, 0.25, 0.35, 0.4, 0.45, 0.4, 0.35, 0.25, 0, 0]
+  embed_slerp: true

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62863b77a195d0b2a5541c83ee9d1e5a01b9fea857dff40435baf91fe6cb0341
+size 3925983664

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a0e2fc78c50f0682a23fda4e5d315cf1dea38e0165748bbfe06ef1ea43c3cc
+size 3900830872

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77012da34be50607e78536cf2090d74fbedcaea1f2b2a8c9d23b32ebcfca4022
+size 3900830864

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d056d203422098b12de9cf49ab0c7fff0d9978fdbd1e7b919da295c89fbe418
+size 3900830872

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b6693e17d4c0aec3d4ce394493c597a5e48a0782eadf946f29320a07b56a9b
+size 3900830864

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d97fcf657ea33c7c71ee45abb56a8806a6030faf75d4ca6e5780341c0ed2456
+size 3900830872

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9ced7cdd425c92379af0a92d71d9a3485943f8bb75725ccffdb233b6ff53bf
+size 3900830872

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb14b27a5809a12d9f7e8ec3e9943c7bf2a5dac0b6b2d7ef702b117ab869305
+size 3900830864

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dad58381d312088bdb1f84b471dd399d1e89be5d2e83a351141d1c693e214b3
+size 3900830872

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04945147abf3927064789a4646a257e45e9b33fc630f718189a3878dea4b43bc
+size 3900830864

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8a3ee8a3e796177a5c04237b24fdd589d064e4d507089a35432a5283c3ace5
+size 3900830848

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f966c6284983c081fa324a33fa71e71bc298aab6fa21bc741703c65eb05ee3f5
+size 1560332320

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 44494565376}, "weight_map": {"lm_head.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583