Hugging Face's logo

huizimao
/
gpt-oss-20b-uncensored-mxfp4

Safetensors
gpt_oss
8-bit precision
mxfp4
Model card Files Community
huizimao commited on
Commit
22a2d02
·
verified ·
1 Parent(s): 9629e36

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. config.json +76 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +467 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +183 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 200002,
8
+ "experts_per_token": 4,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2880,
12
+ "initial_context_length": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2880,
15
+ "layer_types": [
16
+ "sliding_attention",
17
+ "full_attention",
18
+ "sliding_attention",
19
+ "full_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention"
40
+ ],
41
+ "max_position_embeddings": 131072,
42
+ "model_type": "gpt_oss",
43
+ "num_attention_heads": 64,
44
+ "num_experts_per_tok": 4,
45
+ "num_hidden_layers": 24,
46
+ "num_key_value_heads": 8,
47
+ "num_local_experts": 32,
48
+ "output_router_logits": false,
49
+ "pad_token_id": 199999,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "beta_fast": 32.0,
53
+ "beta_slow": 1.0,
54
+ "factor": 32.0,
55
+ "original_max_position_embeddings": 4096,
56
+ "rope_type": "yarn",
57
+ "truncate": false
58
+ },
59
+ "rope_theta": 150000,
60
+ "router_aux_loss_coef": 0.9,
61
+ "sliding_window": 128,
62
+ "swiglu_limit": 7.0,
63
+ "tie_word_embeddings": false,
64
+ "transformers_version": "4.55.0",
65
+ "use_cache": true,
66
+ "vocab_size": 201088,
67
+ "quantization_config": {
68
+ "modules_to_not_convert": [
69
+ "model.layers.*.self_attn",
70
+ "model.layers.*.mlp.router",
71
+ "model.embed_tokens",
72
+ "lm_head"
73
+ ],
74
+ "quant_method": "mxfp4"
75
+ }
76
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.55.0"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749bbd36c00ae7f54d5b1ad450256e9af55395a8e6b86ce64e6c91055b511816
3
+ size 4999744880
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20252c14c366412f851ab510e3ca0fd507373f02f4f5364584c1d1689163c5e2
3
+ size 4795391048
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c17491d3846c21aca08e60352fb827abafe1e09aa1f4de1aa1c439f2116ed12
3
+ size 3966181488
model.safetensors.index.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 20914757184,
4
+ "total_size": 13761264768
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00003-of-00003.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mlp.router.bias": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.mlp.router.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.sinks": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.mlp.router.bias": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.mlp.router.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.self_attn.sinks": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.10.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
49
+ "model.layers.10.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
50
+ "model.layers.10.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
51
+ "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
52
+ "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
53
+ "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
54
+ "model.layers.10.mlp.router.bias": "model-00002-of-00003.safetensors",
55
+ "model.layers.10.mlp.router.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
58
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
60
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
62
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.10.self_attn.sinks": "model-00002-of-00003.safetensors",
64
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
65
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
72
+ "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
73
+ "model.layers.11.mlp.router.bias": "model-00002-of-00003.safetensors",
74
+ "model.layers.11.mlp.router.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
77
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
79
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
81
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.11.self_attn.sinks": "model-00002-of-00003.safetensors",
83
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
84
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
87
+ "model.layers.12.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
88
+ "model.layers.12.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
89
+ "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
90
+ "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
91
+ "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
92
+ "model.layers.12.mlp.router.bias": "model-00002-of-00003.safetensors",
93
+ "model.layers.12.mlp.router.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
96
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.12.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
98
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
100
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.12.self_attn.sinks": "model-00002-of-00003.safetensors",
102
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
103
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.13.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
106
+ "model.layers.13.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
107
+ "model.layers.13.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
108
+ "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
109
+ "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
110
+ "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
111
+ "model.layers.13.mlp.router.bias": "model-00002-of-00003.safetensors",
112
+ "model.layers.13.mlp.router.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
115
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.13.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
117
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
119
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.13.self_attn.sinks": "model-00002-of-00003.safetensors",
121
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
122
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.14.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
125
+ "model.layers.14.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
126
+ "model.layers.14.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
127
+ "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
128
+ "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
129
+ "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
130
+ "model.layers.14.mlp.router.bias": "model-00002-of-00003.safetensors",
131
+ "model.layers.14.mlp.router.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
134
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
136
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
138
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.14.self_attn.sinks": "model-00002-of-00003.safetensors",
140
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
141
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.15.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
144
+ "model.layers.15.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
145
+ "model.layers.15.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
146
+ "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
147
+ "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
148
+ "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
149
+ "model.layers.15.mlp.router.bias": "model-00002-of-00003.safetensors",
150
+ "model.layers.15.mlp.router.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
153
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.15.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
155
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
157
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.15.self_attn.sinks": "model-00002-of-00003.safetensors",
159
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
160
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.16.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
163
+ "model.layers.16.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
164
+ "model.layers.16.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
165
+ "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
166
+ "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
167
+ "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
168
+ "model.layers.16.mlp.router.bias": "model-00002-of-00003.safetensors",
169
+ "model.layers.16.mlp.router.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
172
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.16.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
174
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
176
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.16.self_attn.sinks": "model-00002-of-00003.safetensors",
178
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
179
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.17.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
182
+ "model.layers.17.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
183
+ "model.layers.17.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
184
+ "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
185
+ "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
186
+ "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
187
+ "model.layers.17.mlp.router.bias": "model-00002-of-00003.safetensors",
188
+ "model.layers.17.mlp.router.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
191
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.17.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
193
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
195
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.17.self_attn.sinks": "model-00002-of-00003.safetensors",
197
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
198
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.18.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
201
+ "model.layers.18.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
202
+ "model.layers.18.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
203
+ "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
204
+ "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
205
+ "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
206
+ "model.layers.18.mlp.router.bias": "model-00002-of-00003.safetensors",
207
+ "model.layers.18.mlp.router.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
210
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.18.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
212
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
214
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.18.self_attn.sinks": "model-00002-of-00003.safetensors",
216
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
217
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
219
+ "model.layers.19.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
220
+ "model.layers.19.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
221
+ "model.layers.19.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
222
+ "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
223
+ "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
224
+ "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
225
+ "model.layers.19.mlp.router.bias": "model-00003-of-00003.safetensors",
226
+ "model.layers.19.mlp.router.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
229
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.19.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
231
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
233
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.19.self_attn.sinks": "model-00003-of-00003.safetensors",
235
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
236
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.2.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
239
+ "model.layers.2.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
240
+ "model.layers.2.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
241
+ "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
242
+ "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
243
+ "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
244
+ "model.layers.2.mlp.router.bias": "model-00001-of-00003.safetensors",
245
+ "model.layers.2.mlp.router.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
248
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
250
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
252
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.2.self_attn.sinks": "model-00001-of-00003.safetensors",
254
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
255
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.20.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
258
+ "model.layers.20.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
259
+ "model.layers.20.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
260
+ "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
261
+ "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
262
+ "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
263
+ "model.layers.20.mlp.router.bias": "model-00003-of-00003.safetensors",
264
+ "model.layers.20.mlp.router.weight": "model-00003-of-00003.safetensors",
265
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
267
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.20.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
269
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
271
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.20.self_attn.sinks": "model-00003-of-00003.safetensors",
273
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
274
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.21.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
277
+ "model.layers.21.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
278
+ "model.layers.21.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
279
+ "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
280
+ "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
281
+ "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
282
+ "model.layers.21.mlp.router.bias": "model-00003-of-00003.safetensors",
283
+ "model.layers.21.mlp.router.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
286
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
288
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
290
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.21.self_attn.sinks": "model-00003-of-00003.safetensors",
292
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
293
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.22.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
296
+ "model.layers.22.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
297
+ "model.layers.22.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
298
+ "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
299
+ "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
300
+ "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
301
+ "model.layers.22.mlp.router.bias": "model-00003-of-00003.safetensors",
302
+ "model.layers.22.mlp.router.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
305
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
307
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
309
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.22.self_attn.sinks": "model-00003-of-00003.safetensors",
311
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
312
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
313
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
314
+ "model.layers.23.mlp.experts.down_proj_bias": "model-00003-of-00003.safetensors",
315
+ "model.layers.23.mlp.experts.down_proj_blocks": "model-00003-of-00003.safetensors",
316
+ "model.layers.23.mlp.experts.down_proj_scales": "model-00003-of-00003.safetensors",
317
+ "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00003-of-00003.safetensors",
318
+ "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00003-of-00003.safetensors",
319
+ "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00003-of-00003.safetensors",
320
+ "model.layers.23.mlp.router.bias": "model-00003-of-00003.safetensors",
321
+ "model.layers.23.mlp.router.weight": "model-00003-of-00003.safetensors",
322
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
323
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
324
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
325
+ "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
326
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
327
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
328
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
329
+ "model.layers.23.self_attn.sinks": "model-00003-of-00003.safetensors",
330
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
331
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
332
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.3.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
334
+ "model.layers.3.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
335
+ "model.layers.3.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
336
+ "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
337
+ "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
338
+ "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
339
+ "model.layers.3.mlp.router.bias": "model-00001-of-00003.safetensors",
340
+ "model.layers.3.mlp.router.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
343
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
345
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
347
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.3.self_attn.sinks": "model-00001-of-00003.safetensors",
349
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
350
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.4.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
353
+ "model.layers.4.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
354
+ "model.layers.4.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
355
+ "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
356
+ "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
357
+ "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
358
+ "model.layers.4.mlp.router.bias": "model-00001-of-00003.safetensors",
359
+ "model.layers.4.mlp.router.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
362
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
364
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
366
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.4.self_attn.sinks": "model-00001-of-00003.safetensors",
368
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
369
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
370
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
371
+ "model.layers.5.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
372
+ "model.layers.5.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
373
+ "model.layers.5.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
374
+ "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
375
+ "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
376
+ "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
377
+ "model.layers.5.mlp.router.bias": "model-00001-of-00003.safetensors",
378
+ "model.layers.5.mlp.router.weight": "model-00001-of-00003.safetensors",
379
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
380
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
381
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
382
+ "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
383
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
384
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
385
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
386
+ "model.layers.5.self_attn.sinks": "model-00001-of-00003.safetensors",
387
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
388
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
389
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
390
+ "model.layers.6.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
391
+ "model.layers.6.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
392
+ "model.layers.6.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
393
+ "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
394
+ "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
395
+ "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
396
+ "model.layers.6.mlp.router.bias": "model-00001-of-00003.safetensors",
397
+ "model.layers.6.mlp.router.weight": "model-00001-of-00003.safetensors",
398
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
399
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
400
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
401
+ "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
402
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
403
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
404
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
405
+ "model.layers.6.self_attn.sinks": "model-00001-of-00003.safetensors",
406
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
407
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
408
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
409
+ "model.layers.7.mlp.experts.down_proj_bias": "model-00001-of-00003.safetensors",
410
+ "model.layers.7.mlp.experts.down_proj_blocks": "model-00001-of-00003.safetensors",
411
+ "model.layers.7.mlp.experts.down_proj_scales": "model-00001-of-00003.safetensors",
412
+ "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00001-of-00003.safetensors",
413
+ "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00001-of-00003.safetensors",
414
+ "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00001-of-00003.safetensors",
415
+ "model.layers.7.mlp.router.bias": "model-00001-of-00003.safetensors",
416
+ "model.layers.7.mlp.router.weight": "model-00001-of-00003.safetensors",
417
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
418
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
419
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
420
+ "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
421
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
422
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
423
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
424
+ "model.layers.7.self_attn.sinks": "model-00001-of-00003.safetensors",
425
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
426
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
427
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
428
+ "model.layers.8.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
429
+ "model.layers.8.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
430
+ "model.layers.8.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
431
+ "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
432
+ "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
433
+ "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
434
+ "model.layers.8.mlp.router.bias": "model-00002-of-00003.safetensors",
435
+ "model.layers.8.mlp.router.weight": "model-00002-of-00003.safetensors",
436
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
437
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
438
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
439
+ "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
440
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
441
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
442
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
443
+ "model.layers.8.self_attn.sinks": "model-00001-of-00003.safetensors",
444
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
445
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
447
+ "model.layers.9.mlp.experts.down_proj_bias": "model-00002-of-00003.safetensors",
448
+ "model.layers.9.mlp.experts.down_proj_blocks": "model-00002-of-00003.safetensors",
449
+ "model.layers.9.mlp.experts.down_proj_scales": "model-00002-of-00003.safetensors",
450
+ "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00002-of-00003.safetensors",
451
+ "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00002-of-00003.safetensors",
452
+ "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00002-of-00003.safetensors",
453
+ "model.layers.9.mlp.router.bias": "model-00002-of-00003.safetensors",
454
+ "model.layers.9.mlp.router.weight": "model-00002-of-00003.safetensors",
455
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
456
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
457
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
459
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
460
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
461
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
462
+ "model.layers.9.self_attn.sinks": "model-00002-of-00003.safetensors",
463
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
464
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
465
+ "model.norm.weight": "model-00003-of-00003.safetensors"
466
+ }
467
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
3
+ size 27868174
tokenizer_config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "199998": {
4
+ "content": "<|startoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "199999": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "200000": {
20
+ "content": "<|reserved_200000|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "200001": {
28
+ "content": "<|reserved_200001|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "200002": {
36
+ "content": "<|return|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "200003": {
44
+ "content": "<|constrain|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "200004": {
52
+ "content": "<|reserved_200004|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "200005": {
60
+ "content": "<|channel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "200006": {
68
+ "content": "<|start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "200007": {
76
+ "content": "<|end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "200008": {
84
+ "content": "<|message|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "200009": {
92
+ "content": "<|reserved_200009|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "200010": {
100
+ "content": "<|reserved_200010|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "200011": {
108
+ "content": "<|reserved_200011|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "200012": {
116
+ "content": "<|call|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "200013": {
124
+ "content": "<|reserved_200013|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "200014": {
132
+ "content": "<|reserved_200014|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "200015": {
140
+ "content": "<|reserved_200015|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "200016": {
148
+ "content": "<|reserved_200016|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "200017": {
156
+ "content": "<|reserved_200017|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "200018": {
164
+ "content": "<|endofprompt|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ }
171
+ },
172
+ "bos_token": "<|startoftext|>",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "<|return|>",
175
+ "extra_special_tokens": {},
176
+ "model_input_names": [
177
+ "input_ids",
178
+ "attention_mask"
179
+ ],
180
+ "model_max_length": 1000000000000000019884624838656,
181
+ "pad_token": "<|endoftext|>",
182
+ "tokenizer_class": "PreTrainedTokenizerFast"
183
+ }