LoneStriker commited on
Commit
72062b2
1 Parent(s): 383fb9b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - fr
5
+ - it
6
+ - de
7
+ - es
8
+ - en
9
+ inference: false
10
+ ---
11
+ # Model Card for Mixtral-Fusion-4x7B-Instruct-v0.1
12
+ This model is an experimental model created by merging [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) experts.
13
+
14
+ # How we merged experts
15
+ We simply take the average of every two experts.weight.
16
+ The same goes for gate.weight.
17
+
18
+ # How To Convert
19
+ use colab cpu-high-memory.
20
+ [convert_mixtral_8x7b_to_4x7b.ipynb](https://huggingface.co/mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1/blob/main/notebook/convert_mixtral_8x7b_to_4x7b.ipynb)
21
+
22
+ # Usage
23
+ ~~~python
24
+ pip install git+https://github.com/huggingface/transformers --upgrade
25
+ pip install torch accelerate bitsandbytes flash_attn
26
+ ~~~
27
+
28
+ ~~~python
29
+ from transformers import AutoTokenizer, AutoModelForCausalLM, MixtralForCausalLM
30
+ import torch
31
+
32
+ model_name_or_path = "mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1"
33
+
34
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
35
+ model = MixtralForCausalLM.from_pretrained(model_name_or_path, load_in_8bit=True)
36
+
37
+ # set num_experts_per_tok 1 or 2 ?
38
+ model.config.num_experts_per_tok = 2
39
+
40
+ # message
41
+ messages = [
42
+ {"role": "user", "content": "Tell me what's for dinner tonight."},
43
+ ]
44
+
45
+ with torch.no_grad():
46
+ token_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
47
+ output_ids = model.generate(
48
+ token_ids.to(model.device),
49
+ temperature=0.5,
50
+ do_sample=True,
51
+ top_p=0.95,
52
+ top_k=40,
53
+ max_new_tokens=128,
54
+ repetition_penalty=1.5
55
+ )
56
+ output = tokenizer.decode(output_ids[0][token_ids.size(1) :])
57
+ print(output)
58
+
59
+ ~~~
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/tf_models/mixtral-7bx4",
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": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.37.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,618 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 48307380224
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00010-of-00010.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
20
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
21
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
22
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
23
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
24
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
25
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
26
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
27
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
28
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
29
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
30
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
31
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
32
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
33
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
34
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
35
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
36
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
37
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
38
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
39
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
40
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
41
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
42
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
43
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
44
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
45
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
46
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
47
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
48
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
49
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
50
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
51
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
52
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
53
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
54
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
55
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
56
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
57
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
58
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
59
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors",
60
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
61
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
62
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
63
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
65
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
66
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
67
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
68
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
69
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
70
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
71
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
72
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
73
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
74
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
75
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
76
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
77
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
78
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
79
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
80
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
81
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
82
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
83
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
84
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
85
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
86
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
87
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
88
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
89
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
90
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
91
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
92
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
93
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
94
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
95
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
96
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
97
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
98
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
99
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
100
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
101
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
102
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
103
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
104
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
105
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
106
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
107
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
108
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
109
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
110
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
111
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
112
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
113
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
114
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
115
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
116
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors",
117
+ "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
118
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
119
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
120
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
121
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
122
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
123
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
124
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
125
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
126
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
127
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
128
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
129
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
130
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
131
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
132
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
133
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
134
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
135
+ "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors",
136
+ "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
137
+ "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
138
+ "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
139
+ "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
140
+ "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
141
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
142
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
143
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
144
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
145
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
146
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
147
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
148
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
149
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
150
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
151
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
152
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
153
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
154
+ "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors",
155
+ "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
156
+ "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
157
+ "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
158
+ "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
159
+ "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
160
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
161
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
162
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
163
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
164
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
165
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
166
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
167
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
168
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
169
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
170
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
171
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
172
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
173
+ "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
174
+ "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
175
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
176
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
177
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
178
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
179
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
180
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
181
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
182
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
183
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
184
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
185
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
186
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
187
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
188
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
189
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
190
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
191
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
192
+ "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors",
193
+ "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
194
+ "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
195
+ "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
196
+ "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
197
+ "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
198
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
199
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
200
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
201
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
202
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
203
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
204
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
205
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
206
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
207
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
208
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
209
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
210
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
211
+ "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors",
212
+ "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
213
+ "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
214
+ "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
215
+ "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
216
+ "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
217
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
218
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
219
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
220
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
221
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
222
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
223
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
224
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
225
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
226
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
227
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
228
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
229
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
230
+ "model.layers.19.input_layernorm.weight": "model-00007-of-00010.safetensors",
231
+ "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
232
+ "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
233
+ "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
234
+ "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
235
+ "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
236
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
237
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
238
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
239
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
240
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
241
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
242
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
243
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
244
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
245
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
246
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
247
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
248
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
249
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
250
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
251
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
252
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
253
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
254
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
255
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
256
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
257
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
258
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
259
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
260
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
261
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
262
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
263
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
264
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
265
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
266
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
267
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
268
+ "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors",
269
+ "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
270
+ "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
271
+ "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
272
+ "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
273
+ "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
274
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
275
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
276
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
277
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
278
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
279
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
280
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
281
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
282
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
283
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
284
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
285
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
286
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
287
+ "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors",
288
+ "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
289
+ "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
290
+ "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
291
+ "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
292
+ "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
293
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
294
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
295
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
296
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
297
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
298
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
299
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
300
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
301
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
302
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
303
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
304
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
305
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
306
+ "model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors",
307
+ "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
308
+ "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
309
+ "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
310
+ "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
311
+ "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
312
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
313
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
314
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
315
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
316
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
317
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
318
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
319
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
320
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
321
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
322
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
323
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
324
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
325
+ "model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors",
326
+ "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
327
+ "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
328
+ "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
329
+ "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
330
+ "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
331
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
332
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
333
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
334
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
335
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
336
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
337
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
338
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
339
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
340
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
341
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
342
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
343
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
344
+ "model.layers.24.input_layernorm.weight": "model-00008-of-00010.safetensors",
345
+ "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
346
+ "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
347
+ "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
348
+ "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
349
+ "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
350
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
351
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
352
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
353
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
354
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
355
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
356
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
357
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
358
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
359
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
360
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
361
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
362
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
363
+ "model.layers.25.input_layernorm.weight": "model-00008-of-00010.safetensors",
364
+ "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
365
+ "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
366
+ "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
367
+ "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
368
+ "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
369
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
370
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
371
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
372
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
373
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
374
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
375
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
376
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
377
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
378
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
379
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
380
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
381
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
382
+ "model.layers.26.input_layernorm.weight": "model-00009-of-00010.safetensors",
383
+ "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
384
+ "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
385
+ "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
386
+ "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
387
+ "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
388
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
389
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
390
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
391
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
392
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
393
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
394
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
395
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
396
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
397
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
398
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
399
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
400
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
401
+ "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors",
402
+ "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
403
+ "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
404
+ "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
405
+ "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
406
+ "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
407
+ "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
408
+ "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
409
+ "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
410
+ "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
411
+ "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
412
+ "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
413
+ "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
414
+ "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
415
+ "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
416
+ "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
417
+ "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
418
+ "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
419
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
420
+ "model.layers.28.input_layernorm.weight": "model-00009-of-00010.safetensors",
421
+ "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
422
+ "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
423
+ "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
424
+ "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
425
+ "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
426
+ "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
427
+ "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
428
+ "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
429
+ "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
430
+ "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
431
+ "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
432
+ "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
433
+ "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
434
+ "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
435
+ "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
436
+ "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
437
+ "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
438
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
439
+ "model.layers.29.input_layernorm.weight": "model-00010-of-00010.safetensors",
440
+ "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
441
+ "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
442
+ "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
443
+ "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
444
+ "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
445
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
446
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
447
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
448
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
449
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
450
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
451
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
452
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
453
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
454
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
455
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
456
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
457
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
458
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
459
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
460
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
461
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
462
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
463
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
464
+ "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors",
465
+ "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors",
466
+ "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors",
467
+ "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors",
468
+ "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors",
469
+ "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors",
470
+ "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors",
471
+ "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors",
472
+ "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
473
+ "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
474
+ "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
475
+ "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
476
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors",
477
+ "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors",
478
+ "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
479
+ "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
480
+ "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
481
+ "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
482
+ "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
483
+ "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors",
484
+ "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors",
485
+ "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors",
486
+ "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors",
487
+ "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors",
488
+ "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors",
489
+ "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors",
490
+ "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors",
491
+ "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
492
+ "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
493
+ "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
494
+ "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
495
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors",
496
+ "model.layers.31.input_layernorm.weight": "model-00010-of-00010.safetensors",
497
+ "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
498
+ "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
499
+ "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
500
+ "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
501
+ "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
502
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
503
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
504
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
505
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
506
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
507
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
508
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
509
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
510
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
511
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
512
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
513
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
514
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
515
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
516
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
517
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
518
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
519
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
520
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
521
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
522
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
523
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
524
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
525
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
526
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
527
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
528
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
529
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
530
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
531
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
532
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
533
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
534
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
535
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
536
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
537
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
538
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
539
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
540
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
541
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
542
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
543
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
544
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
545
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
546
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
547
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
548
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
549
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
550
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
551
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
552
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
553
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
554
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
555
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
556
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
557
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
558
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
559
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
560
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
561
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
562
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
563
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
564
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
565
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
566
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
567
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
568
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
569
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
570
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
571
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
572
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
573
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
574
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
575
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
576
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
577
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
578
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
579
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
580
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
581
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
582
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
583
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
584
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
585
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
586
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
587
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
588
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
589
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
590
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
591
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
592
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
593
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
594
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
595
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
596
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
597
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
598
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
599
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
600
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
601
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
602
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
603
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
604
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
605
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
606
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
607
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
608
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
609
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
610
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00010.safetensors",
611
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
612
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
613
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
614
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
615
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
616
+ "model.norm.weight": "model-00010-of-00010.safetensors"
617
+ }
618
+ }
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df03b153daef993ed87aaa9ba670bc4e8a1c814037f640c6e32b14a5267496fa
3
+ size 8568865776
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b07bcd804d555ee096b56b1e3d637e28ab6a7975f6f1683176f7a49fc205c82
3
+ size 3757700184
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }