gagan3012 commited on
Commit
4b959fa
1 Parent(s): db2a604

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - mixtral
6
+ - openchat/openchat-3.5-0106
7
+ - giux78/zefiro-7b-beta-ITA-v0.1
8
+ - azale-ai/Starstreak-7b-beta
9
+ - gagan3012/Mistral_arabic_dpo
10
+ - davidkim205/komt-mistral-7b-v1
11
+ - OpenBuddy/openbuddy-zephyr-7b-v14.1
12
+ - manishiitg/open-aditi-hi-v1
13
+ - VAGOsolutions/SauerkrautLM-7b-v1-mistral
14
+ ---
15
+
16
+ # Multilingual-mistral
17
+
18
+ This model is a Mixure of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
19
+ * [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
20
+ * [giux78/zefiro-7b-beta-ITA-v0.1](https://huggingface.co/giux78/zefiro-7b-beta-ITA-v0.1)
21
+ * [azale-ai/Starstreak-7b-beta](https://huggingface.co/azale-ai/Starstreak-7b-beta)
22
+ * [gagan3012/Mistral_arabic_dpo](https://huggingface.co/gagan3012/Mistral_arabic_dpo)
23
+ * [davidkim205/komt-mistral-7b-v1](https://huggingface.co/davidkim205/komt-mistral-7b-v1)
24
+ * [OpenBuddy/openbuddy-zephyr-7b-v14.1](https://huggingface.co/OpenBuddy/openbuddy-zephyr-7b-v14.1)
25
+ * [manishiitg/open-aditi-hi-v1](https://huggingface.co/manishiitg/open-aditi-hi-v1)
26
+ * [VAGOsolutions/SauerkrautLM-7b-v1-mistral](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral)
27
+
28
+ ## 🧩 Configuration
29
+
30
+ ```yamlbase_model: mistralai/Mistral-7B-Instruct-v0.2
31
+ dtype: bfloat16
32
+ experts:
33
+ - positive_prompts:
34
+ - chat
35
+ - assistant
36
+ - tell me
37
+ - explain
38
+ source_model: openchat/openchat-3.5-0106
39
+ - positive_prompts:
40
+ - chat
41
+ - assistant
42
+ - tell me
43
+ - explain
44
+ source_model: giux78/zefiro-7b-beta-ITA-v0.1
45
+ - positive_prompts:
46
+ - indonesian
47
+ - indonesia
48
+ - answer in indonesian
49
+ source_model: azale-ai/Starstreak-7b-beta
50
+ - positive_prompts:
51
+ - arabic
52
+ - arab
53
+ - arabia
54
+ - answer in arabic
55
+ source_model: gagan3012/Mistral_arabic_dpo
56
+ - positive_prompts:
57
+ - korean
58
+ - answer in korean
59
+ - korea
60
+ source_model: davidkim205/komt-mistral-7b-v1
61
+ - positive_prompts:
62
+ - chinese
63
+ - china
64
+ - answer in chinese
65
+ source_model: OpenBuddy/openbuddy-zephyr-7b-v14.1
66
+ - positive_prompts:
67
+ - hindi
68
+ - india
69
+ - hindu
70
+ - answer in hindi
71
+ source_model: manishiitg/open-aditi-hi-v1
72
+ - positive_prompts:
73
+ - german
74
+ - germany
75
+ - answer in german
76
+ - deutsch
77
+ source_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
78
+ gate_mode: hidden
79
+ ```
80
+
81
+ ## 💻 Usage
82
+
83
+ ```python
84
+ !pip install -qU transformers bitsandbytes accelerate
85
+
86
+ from transformers import AutoTokenizer
87
+ import transformers
88
+ import torch
89
+
90
+ model = "gagan3012/Multilingual-mistral"
91
+
92
+ tokenizer = AutoTokenizer.from_pretrained(model)
93
+ pipeline = transformers.pipeline(
94
+ "text-generation",
95
+ model=model,
96
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
97
+ )
98
+
99
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
100
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
101
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
102
+ print(outputs[0]["generated_text"])
103
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.36.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: openchat/openchat-3.5-0106
6
+ positive_prompts:
7
+ - "chat"
8
+ - "assistant"
9
+ - "tell me"
10
+ - "explain"
11
+ - source_model: giux78/zefiro-7b-beta-ITA-v0.1
12
+ positive_prompts:
13
+ - "chat"
14
+ - "assistant"
15
+ - "tell me"
16
+ - "explain"
17
+ - source_model: azale-ai/Starstreak-7b-beta
18
+ positive_prompts:
19
+ - "indonesian"
20
+ - "indonesia"
21
+ - "answer in indonesian"
22
+ - source_model: gagan3012/Mistral_arabic_dpo
23
+ positive_prompts:
24
+ - "arabic"
25
+ - "arab"
26
+ - "arabia"
27
+ - "answer in arabic"
28
+ - source_model: davidkim205/komt-mistral-7b-v1
29
+ positive_prompts:
30
+ - "korean"
31
+ - "answer in korean"
32
+ - "korea"
33
+ - source_model: OpenBuddy/openbuddy-zephyr-7b-v14.1
34
+ positive_prompts:
35
+ - "chinese"
36
+ - "china"
37
+ - "answer in chinese"
38
+ - source_model: manishiitg/open-aditi-hi-v1
39
+ positive_prompts:
40
+ - "hindi"
41
+ - "india"
42
+ - "hindu"
43
+ - "answer in hindi"
44
+ - source_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
45
+ positive_prompts:
46
+ - "german"
47
+ - "germany"
48
+ - "answer in german"
49
+ - "deutsch"
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1437cbfd56a25279bae5dd7076c781610ed0495dfcb3d55e25e933f503b4d1e6
3
+ size 9919813664
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3deee21b16e942927a796b14c8b1db9d628879c647a1ac260e7ef3031a488607
3
+ size 9982454760
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8ee33270f019e79d5c3be875d0951debd95636506e2c30657216a8d5e37fe0
3
+ size 9982454760
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df93a65ebea0a9bc7d1f9c6ea92782a4bb0d2bef231b1b9fc5a62cf64595541
3
+ size 9982454680
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ea63f9e1e6369e7534fb594fc5819ab13bf7d19daedad71892b823bd4bab6e
3
+ size 9982454760
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3452885b9be3af6ac031bda3d966f6e0e545587a6937e929b195cbaa13850685
3
+ size 9982454760
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e86ca19a3990561ffbe20971bdb6ffae22b2a5e6740abcb915441a50a726ce
3
+ size 9982454680
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37239482f58c408491d20b1b193c95c0a93c8db6a2c5f18cfa9976fe05221e31
3
+ size 9982454760
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976e2244b8fea62eeea958d43f5383156311d36d912b383fd2d07dfb40ba4dcd
3
+ size 9982454760
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fb4b96eb5b70260faae87dc52c23cca089ff4f19e9a2459db0a99325797468
3
+ size 3626261624
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-00010.safetensors", "model.norm.weight": "model-00001-of-00010.safetensors", "lm_head.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors"}}
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
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
+ }