Steelskull commited on
Commit
0c39869
1 Parent(s): 853b7ab

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - moe
5
+ - merge
6
+ - mergekit
7
+ - kodonho/SolarM-SakuraSolar-SLERP
8
+ - Sao10K/Sensualize-Solar-10.7B
9
+ - NousResearch/Nous-Hermes-2-SOLAR-10.7B
10
+ - fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
11
+ ---
12
+
13
+ # Umbra-MoE-4x10.7
14
+
15
+ Umbra-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [kodonho/SolarM-SakuraSolar-SLERP](https://huggingface.co/kodonho/SolarM-SakuraSolar-SLERP)
17
+ * [Sao10K/Sensualize-Solar-10.7B](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B)
18
+ * [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B)
19
+ * [fblgit/UNA-SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0)
20
+
21
+ ## 🧩 Configuration
22
+
23
+ ```yamlbase_model: kodonho/SolarM-SakuraSolar-SLERP
24
+ gate_mode: hidden
25
+ dtype: bfloat16
26
+ experts:
27
+ - source_model: kodonho/SolarM-SakuraSolar-SLERP
28
+ positive_prompts:
29
+ - "versatile"
30
+ - "helpful"
31
+ - "factual"
32
+ - "integrated"
33
+ - "adaptive"
34
+ - "comprehensive"
35
+ - "balanced"
36
+ negative_prompts:
37
+ - "specialized"
38
+ - "narrow"
39
+ - "focused"
40
+ - "limited"
41
+ - "specific"
42
+
43
+ - source_model: Sao10K/Sensualize-Solar-10.7B
44
+ positive_prompts:
45
+ - "creative"
46
+ - "chat"
47
+ - "discuss"
48
+ - "culture"
49
+ - "world"
50
+ - "expressive"
51
+ - "detailed"
52
+ - "imaginative"
53
+ - "engaging"
54
+ negative_prompts:
55
+ - "sorry"
56
+ - "cannot"
57
+ - "factual"
58
+ - "concise"
59
+ - "straightforward"
60
+ - "objective"
61
+ - "dry"
62
+
63
+ - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
64
+ positive_prompts:
65
+ - "analytical"
66
+ - "accurate"
67
+ - "logical"
68
+ - "knowledgeable"
69
+ - "precise"
70
+ - "calculate"
71
+ - "compute"
72
+ - "solve"
73
+ - "work"
74
+ - "python"
75
+ - "javascript"
76
+ - "programming"
77
+ - "algorithm"
78
+ - "tell me"
79
+ - "assistant"
80
+ negative_prompts:
81
+ - "creative"
82
+ - "abstract"
83
+ - "imaginative"
84
+ - "artistic"
85
+ - "emotional"
86
+ - "mistake"
87
+ - "inaccurate"
88
+
89
+ - source_model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
90
+ positive_prompts:
91
+ - "instructive"
92
+ - "clear"
93
+ - "directive"
94
+ - "helpful"
95
+ - "informative"
96
+ negative_prompts:
97
+ - "exploratory"
98
+ - "open-ended"
99
+ - "narrative"
100
+ - "speculative"
101
+ - "artistic"
102
+ ```
103
+
104
+ ## 💻 Usage
105
+
106
+ ```python
107
+ !pip install -qU transformers bitsandbytes accelerate
108
+
109
+ from transformers import AutoTokenizer
110
+ import transformers
111
+ import torch
112
+
113
+ model = "Steelskull/Umbra-MoE-4x10.7"
114
+
115
+ tokenizer = AutoTokenizer.from_pretrained(model)
116
+ pipeline = transformers.pipeline(
117
+ "text-generation",
118
+ model=model,
119
+ model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
120
+ )
121
+
122
+ messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
123
+ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
124
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
125
+ print(outputs[0]["generated_text"])
126
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kodonho/SolarM-SakuraSolar-SLERP",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 48,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 4,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.36.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32000
34
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: kodonho/SolarM-SakuraSolar-SLERP
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: kodonho/SolarM-SakuraSolar-SLERP
6
+ positive_prompts:
7
+ - "versatile"
8
+ - "helpful"
9
+ - "factual"
10
+ - "integrated"
11
+ - "adaptive"
12
+ - "comprehensive"
13
+ - "balanced"
14
+ negative_prompts:
15
+ - "specialized"
16
+ - "narrow"
17
+ - "focused"
18
+ - "limited"
19
+ - "specific"
20
+
21
+ - source_model: Sao10K/Sensualize-Solar-10.7B
22
+ positive_prompts:
23
+ - "creative"
24
+ - "chat"
25
+ - "discuss"
26
+ - "culture"
27
+ - "world"
28
+ - "expressive"
29
+ - "detailed"
30
+ - "imaginative"
31
+ - "engaging"
32
+ negative_prompts:
33
+ - "sorry"
34
+ - "cannot"
35
+ - "factual"
36
+ - "concise"
37
+ - "straightforward"
38
+ - "objective"
39
+ - "dry"
40
+
41
+ - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
42
+ positive_prompts:
43
+ - "analytical"
44
+ - "accurate"
45
+ - "logical"
46
+ - "knowledgeable"
47
+ - "precise"
48
+ - "calculate"
49
+ - "compute"
50
+ - "solve"
51
+ - "work"
52
+ - "python"
53
+ - "javascript"
54
+ - "programming"
55
+ - "algorithm"
56
+ - "tell me"
57
+ - "assistant"
58
+ negative_prompts:
59
+ - "creative"
60
+ - "abstract"
61
+ - "imaginative"
62
+ - "artistic"
63
+ - "emotional"
64
+ - "mistake"
65
+ - "inaccurate"
66
+
67
+ - source_model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
68
+ positive_prompts:
69
+ - "instructive"
70
+ - "clear"
71
+ - "directive"
72
+ - "helpful"
73
+ - "informative"
74
+ negative_prompts:
75
+ - "exploratory"
76
+ - "open-ended"
77
+ - "narrative"
78
+ - "speculative"
79
+ - "artistic"
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2f2b3150f93b645edc36f7ac95c497a34ab9a42c0bf9fca27fe0aee3b4e70f
3
+ size 9919946568
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486c92ec3b91eb8fe0ceba368d9dd33327c2d10bbb9af93d189010d5f9b42301
3
+ size 9982454760
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffeb212b7297a6612ef512f98f0b0c074a7f1f272f0aa867bdfc459c88358ed9
3
+ size 9982454720
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ade7fff1c14a9c655267dc5ebfd9e2c35c8055deb8c9c5face2a5e5fccad72
3
+ size 9982454760
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a1924065873761a668e4f2280edd5fc2824b246419438b4e41c7cd5ec76c92
3
+ size 9982454720
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99cb9d9b09aa9372281659c8836c5078eb40e09b9c50480dfbab3c56b58afe1d
3
+ size 9982454752
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86efbe5354e2f5b3fa301d9d8f9a08d80adbe360f40e609ede9b18afcae31251
3
+ size 9999635384
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8052f830b5adfd9006302578eb48e9cefb341c088ee179d8257afcbb69b583b1
3
+ size 2367182184
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-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00008.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": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% 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": true
43
+ }