LoneStriker commited on
Commit
c813a4a
1 Parent(s): afb4d32

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: yi-license
4
+ license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
5
+ tags:
6
+ - yi
7
+ - moe
8
+ ---
9
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/mLH2E0dk9On_LcFX9yhuS.jpeg)
10
+
11
+ # Bagel-Hermes-2x34B
12
+
13
+ This is the model for Bagel-Hermes-2x34B. I used [mergekit](https://github.com/cg123/mergekit) to make this MOE model.
14
+
15
+ # Prompt Template(s):
16
+
17
+ Since [bagel-dpo-34b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2) uses many prompt templates, and [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) uses ChatML, you can utilize ChatML and other prompt templates provided by bagel.
18
+
19
+ **Note:** I currently do not know which prompt template is best.
20
+
21
+ ### ChatML:
22
+
23
+ ```
24
+ <|im_start|>system
25
+ {system}<|im_end|>
26
+ <|im_start|>user
27
+ {user}<|im_end|>
28
+ <|im_start|>assistant
29
+ {asistant}<|im_end|>
30
+ ```
31
+
32
+ ### Alpaca (sort of)
33
+
34
+ ```
35
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
36
+
37
+ ### Instruction:
38
+ {system}
39
+ {instruction}
40
+
41
+ ### Response:
42
+ ```
43
+ ### Vicuna
44
+
45
+ ```
46
+ {system}
47
+ USER: {instruction}
48
+ ASSISTANT:
49
+ ```
50
+
51
+ Visit [bagel-dpo-34b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2) to try more prompt templates.
52
+
53
+ # Yaml Config to reproduce
54
+
55
+ ```yaml
56
+ base_model: nontoxic-bagel-34b-v0.2
57
+ gate_mode: hidden
58
+ dtype: bfloat16
59
+
60
+ experts:
61
+ - source_model: bagel-dpo-34b-v0.2
62
+ positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]
63
+
64
+ - source_model: Nous-Hermes-2-Yi-34B
65
+ positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
66
+ ```
67
+
68
+ # Quantizationed versions
69
+
70
+ Quantizationed versions of this model is available thanks to [TheBloke](https://hf.co/TheBloke).
71
+
72
+ ##### GPTQ
73
+
74
+ - [TheBloke/Bagel-Hermes-2x34B-GPTQ](https://huggingface.co/TheBloke/Bagel-Hermes-2x34B-GPTQ)
75
+
76
+ ##### GGUF
77
+
78
+ - [TheBloke/Bagel-Hermes-2x34B-GGUF](https://huggingface.co/TheBloke/Bagel-Hermes-2x34B-GGUF)
79
+
80
+ ##### AWQ
81
+
82
+ - [TheBloke/Bagel-Hermes-2x34B-AWQ](https://huggingface.co/TheBloke/Bagel-Hermes-2x34B-AWQ)
83
+
84
+ If you would like to support me:
85
+
86
+ [☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nontoxic-bagel-34b-v0.2",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 20480,
14
+ "max_position_embeddings": 200000,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 56,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 60,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 5000000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.36.2",
32
+ "use_cache": true,
33
+ "vocab_size": 64000
34
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: nontoxic-bagel-34b-v0.2
3
+ gate_mode: hidden
4
+ dtype: bfloat16
5
+
6
+ experts:
7
+ - source_model: bagel-dpo-34b-v0.2
8
+ positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]
9
+
10
+ - source_model: Nous-Hermes-2-Yi-34B
11
+ positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}
output-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7bf8bcc7475dfa857ee39ae2a583179caaf423224fade40e55cafe048650a0
3
+ size 8572660560
output-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5a99bba85f1fa1ce6c257c3982df672b1f77d8fc0e10de604d91eabd137359
3
+ size 8588196128
output-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c8208ada0837d62d8844dbac0bbc695f73678f56e21bd863bb9d7774b6d912
3
+ size 6608891064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 200000,
36
+ "pad_token": "<s>",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }