MarsupialAI commited on
Commit
167a009
1 Parent(s): 6d490ce

Upload 7 files

Browse files
3.5bpw/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "f:\\Aqueducts\\Thermae",
3
+ "antemplate": "[Genre: <|>]",
4
+ "architectures": [
5
+ "MistralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 80,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.40.0.dev0",
25
+ "use_cache": false,
26
+ "vocab_size": 32000,
27
+ "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (Mistral 7B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind.",
28
+ "quantization_config": {
29
+ "quant_method": "exl2",
30
+ "version": "0.0.18",
31
+ "bits": 3.5,
32
+ "head_bits": 6,
33
+ "calibration": {
34
+ "rows": 100,
35
+ "length": 2048,
36
+ "dataset": "(default)"
37
+ }
38
+ }
39
+ }
3.5bpw/mergekit_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: float16
2
+ merge_method: linear
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 80]
6
+ model: f:\Aqueducts\Thermae
7
+ parameters:
8
+ weight: 0.5
9
+ - layer_range: [0, 80]
10
+ model: f:\Aqueducts\Circuses
11
+ parameters:
12
+ weight: 0.5
3.5bpw/model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors"}}
3.5bpw/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
3.5bpw/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
3.5bpw/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
3.5bpw/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }