Hugging Face's logo

piuzha
/
llm_ckpts

Model card Files Community
pz commited on
Commit
0d970fb
·
1 Parent(s): c4f7dfb

initial model upload

Browse files
Files changed (19) hide show
  1. llm_50steps/config.json +28 -0
  2. llm_50steps/generation_config.json +6 -0
  3. llm_50steps/pytorch_model-00001.bin +3 -0
  4. llm_50steps/pytorch_model-00002.bin +3 -0
  5. llm_50steps/pytorch_model-00003.bin +3 -0
  6. llm_50steps/pytorch_model-00004.bin +3 -0
  7. llm_50steps/pytorch_model-00005.bin +3 -0
  8. llm_50steps/pytorch_model-00006.bin +3 -0
  9. llm_50steps/pytorch_model-00007.bin +3 -0
  10. llm_50steps/pytorch_model-00008.bin +3 -0
  11. llm_50steps/pytorch_model-00009.bin +3 -0
  12. llm_50steps/pytorch_model-00010.bin +3 -0
  13. llm_50steps/pytorch_model-00011.bin +3 -0
  14. llm_50steps/pytorch_model-00012.bin +3 -0
  15. llm_50steps/pytorch_model-00013.bin +3 -0
  16. llm_50steps/pytorch_model-00014.bin +3 -0
  17. llm_50steps/pytorch_model-00015.bin +3 -0
  18. llm_50steps/pytorch_model-00016.bin +3 -0
  19. llm_50steps/pytorch_model.bin.index.json +334 -0
llm_50steps/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/shared/user90/workspace/llama-factory/LLaMA-Factory/models/mistral-v0.2-7b-36layers",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
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": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 36,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.33.3",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
llm_50steps/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": "4.33.3"
6
+ }
llm_50steps/pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0462e38be8b98e7d0f320aec5d9b34a9c0aa9ae31244963244bf154e45474a7e
3
+ size 1017140493
llm_50steps/pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498f89095c942f48830d682d77909fc2563db9fcca441e6394bb8c4775832ca4
3
+ size 1040244373
llm_50steps/pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18fcac9833e3d5ddaa17082e61419c1cc1bde29794f7deb98cedae327b1d3aec
3
+ size 1023449521
llm_50steps/pytorch_model-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cede34d0d04a699979b06fd2ee870d1ce8a30f88528779ac2c3c83b36e96eaa3
3
+ size 989894824
llm_50steps/pytorch_model-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad10df0a37f53e4aa04f1c91d26d0f317fa2d1dcff074adec13a1d73869b5767
3
+ size 1040244373
llm_50steps/pytorch_model-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c8289073ce07a463b53de5606772526295627ff3acea7687cdba6258ced505
3
+ size 1023449585
llm_50steps/pytorch_model-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b8170c8c7980d9334f0572c277d3d88eb93c4c2a76ac680a417c569f714af1
3
+ size 989894824
llm_50steps/pytorch_model-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0564c608c3d1b5ed6b7d8977b493c87f549daf330cf1db98db5ad314657178fe
3
+ size 1040244373
llm_50steps/pytorch_model-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00438055b40a88d6f3d19c540beb44e35b99b388e625b75a35c2ac1a75de80c3
3
+ size 1023449585
llm_50steps/pytorch_model-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc86edcc1e288d9b7bec8730743d6342b48388b8ea41331d12ae5065ad43fb3
3
+ size 989894824
llm_50steps/pytorch_model-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f5da162f70fc804e1c9c9e684af96d7bab0ee4bbf09b2b7a6da0db196878dd
3
+ size 1040244373
llm_50steps/pytorch_model-00012.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc7e84485f15de8234557a847604772a3bcc01328caaae1fd4efb7cae36da38
3
+ size 1023449585
llm_50steps/pytorch_model-00013.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5144ab876b9667ce359abf7f0d10d7780f6132170dfc36df935c3baa11a6fa10
3
+ size 989894824
llm_50steps/pytorch_model-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd78591a870f9ef92366231783b9bc830b57d35349548eeddeb019a79461292
3
+ size 1040244373
llm_50steps/pytorch_model-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2936527d0e0909a0a42649c6e252d7b6adc750d362959d609afa7e89b216e72
3
+ size 1023449585
llm_50steps/pytorch_model-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a911145633fd609529860554d1588c5b69e49127effff85e4f5e9e01f176de93
3
+ size 933278660
llm_50steps/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,334 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15476.5703125
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001.bin",
7
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001.bin",
8
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001.bin",
9
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001.bin",
10
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001.bin",
13
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001.bin",
14
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001.bin",
15
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001.bin",
16
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001.bin",
17
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001.bin",
18
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001.bin",
19
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001.bin",
22
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002.bin",
23
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002.bin",
25
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002.bin",
26
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002.bin",
27
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002.bin",
28
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002.bin",
29
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002.bin",
30
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002.bin",
31
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002.bin",
32
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002.bin",
33
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002.bin",
34
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002.bin",
35
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002.bin",
36
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002.bin",
37
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002.bin",
38
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002.bin",
39
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002.bin",
40
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002.bin",
41
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002.bin",
42
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002.bin",
43
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002.bin",
44
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002.bin",
45
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002.bin",
46
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003.bin",
47
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003.bin",
48
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003.bin",
49
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003.bin",
50
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003.bin",
51
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003.bin",
52
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003.bin",
53
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003.bin",
54
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003.bin",
55
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003.bin",
56
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003.bin",
57
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003.bin",
58
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003.bin",
59
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00003.bin",
60
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003.bin",
61
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003.bin",
62
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003.bin",
63
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003.bin",
64
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003.bin",
65
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003.bin",
66
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004.bin",
67
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004.bin",
68
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004.bin",
69
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004.bin",
70
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004.bin",
71
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004.bin",
72
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004.bin",
73
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004.bin",
74
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004.bin",
75
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004.bin",
76
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004.bin",
77
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00004.bin",
78
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004.bin",
79
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004.bin",
80
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004.bin",
81
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004.bin",
82
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004.bin",
83
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004.bin",
84
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004.bin",
85
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005.bin",
86
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00005.bin",
87
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005.bin",
88
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005.bin",
89
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005.bin",
90
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005.bin",
91
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005.bin",
92
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005.bin",
93
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005.bin",
94
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005.bin",
95
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00005.bin",
96
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005.bin",
97
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005.bin",
98
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005.bin",
99
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005.bin",
100
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005.bin",
101
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005.bin",
102
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005.bin",
103
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005.bin",
104
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00005.bin",
105
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005.bin",
106
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005.bin",
107
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005.bin",
108
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005.bin",
109
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006.bin",
110
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006.bin",
111
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006.bin",
112
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006.bin",
113
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00006.bin",
114
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006.bin",
115
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006.bin",
116
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006.bin",
117
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006.bin",
118
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006.bin",
119
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006.bin",
120
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006.bin",
121
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006.bin",
122
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00006.bin",
123
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006.bin",
124
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006.bin",
125
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006.bin",
126
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006.bin",
127
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006.bin",
128
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006.bin",
129
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007.bin",
130
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007.bin",
131
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00007.bin",
132
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007.bin",
133
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007.bin",
134
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007.bin",
135
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007.bin",
136
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007.bin",
137
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007.bin",
138
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007.bin",
139
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007.bin",
140
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00007.bin",
141
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007.bin",
142
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007.bin",
143
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007.bin",
144
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007.bin",
145
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007.bin",
146
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007.bin",
147
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007.bin",
148
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008.bin",
149
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00008.bin",
150
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008.bin",
151
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008.bin",
152
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008.bin",
153
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008.bin",
154
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008.bin",
155
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008.bin",
156
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008.bin",
157
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008.bin",
158
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00008.bin",
159
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008.bin",
160
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008.bin",
161
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008.bin",
162
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008.bin",
163
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008.bin",
164
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008.bin",
165
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008.bin",
166
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00008.bin",
167
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00008.bin",
168
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008.bin",
169
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008.bin",
170
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008.bin",
171
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008.bin",
172
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009.bin",
173
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009.bin",
174
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009.bin",
175
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009.bin",
176
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00009.bin",
177
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009.bin",
178
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009.bin",
179
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009.bin",
180
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009.bin",
181
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009.bin",
182
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009.bin",
183
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009.bin",
184
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009.bin",
185
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00009.bin",
186
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009.bin",
187
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009.bin",
188
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009.bin",
189
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009.bin",
190
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009.bin",
191
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009.bin",
192
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010.bin",
193
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010.bin",
194
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00010.bin",
195
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010.bin",
196
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010.bin",
197
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010.bin",
198
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010.bin",
199
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010.bin",
200
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010.bin",
201
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010.bin",
202
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010.bin",
203
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00010.bin",
204
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010.bin",
205
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010.bin",
206
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010.bin",
207
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010.bin",
208
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010.bin",
209
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010.bin",
210
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00010.bin",
211
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011.bin",
212
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00011.bin",
213
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011.bin",
214
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011.bin",
215
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011.bin",
216
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011.bin",
217
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011.bin",
218
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011.bin",
219
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011.bin",
220
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011.bin",
221
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00011.bin",
222
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011.bin",
223
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011.bin",
224
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011.bin",
225
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011.bin",
226
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011.bin",
227
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011.bin",
228
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011.bin",
229
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00011.bin",
230
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00011.bin",
231
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011.bin",
232
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011.bin",
233
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011.bin",
234
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011.bin",
235
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012.bin",
236
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012.bin",
237
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012.bin",
238
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012.bin",
239
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00012.bin",
240
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012.bin",
241
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012.bin",
243
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012.bin",
244
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012.bin",
245
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012.bin",
246
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012.bin",
247
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012.bin",
248
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00012.bin",
249
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012.bin",
250
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012.bin",
251
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012.bin",
252
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012.bin",
253
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012.bin",
254
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012.bin",
255
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013.bin",
256
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013.bin",
257
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00013.bin",
258
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013.bin",
259
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013.bin",
260
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013.bin",
261
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013.bin",
262
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013.bin",
263
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013.bin",
264
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013.bin",
265
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013.bin",
266
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00013.bin",
267
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013.bin",
268
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013.bin",
269
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013.bin",
270
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013.bin",
271
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013.bin",
272
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013.bin",
273
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00013.bin",
274
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014.bin",
275
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00014.bin",
276
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014.bin",
277
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014.bin",
278
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014.bin",
279
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014.bin",
280
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014.bin",
281
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014.bin",
282
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014.bin",
283
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014.bin",
284
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00014.bin",
285
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014.bin",
286
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014.bin",
287
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014.bin",
288
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014.bin",
289
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014.bin",
290
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014.bin",
291
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014.bin",
292
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00014.bin",
293
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00014.bin",
294
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014.bin",
295
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00014.bin",
296
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00014.bin",
297
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00014.bin",
298
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00015.bin",
299
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00015.bin",
300
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00015.bin",
301
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00015.bin",
302
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00015.bin",
303
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00015.bin",
304
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00015.bin",
305
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00015.bin",
306
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00015.bin",
307
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00015.bin",
308
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00015.bin",
309
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00015.bin",
310
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00015.bin",
311
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00015.bin",
312
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00015.bin",
313
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00015.bin",
314
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00015.bin",
315
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00015.bin",
316
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00015.bin",
317
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00015.bin",
318
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00016.bin",
319
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00016.bin",
320
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00016.bin",
321
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00016.bin",
322
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00016.bin",
323
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00016.bin",
324
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00016.bin",
325
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00016.bin",
326
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00016.bin",
327
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00016.bin",
328
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00016.bin",
329
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00016.bin",
330
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00016.bin",
331
+ "model.norm.weight": "pytorch_model-00016.bin",
332
+ "lm_head.weight": "pytorch_model-00016.bin"
333
+ }
334
+ }