yhyu13 commited on
Commit
33bd671
1 Parent(s): 05934ae
README.md CHANGED
@@ -1,3 +1,49 @@
1
  ---
2
  license: llama2
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
  ---
4
+
5
+ # LM-cocktail 10.7B v1
6
+
7
+
8
+ This is a 50%-50% model of the SOLAR model and meow.
9
+
10
+ https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
11
+
12
+ https://huggingface.co/rishiraj/meow
13
+
14
+
15
+ who rank #1 and #2 among models <13B in the https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard by 2023/12/20.
16
+
17
+
18
+ # Code
19
+
20
+ The LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534
21
+
22
+ Code is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git
23
+
24
+ Merging scripts available under the [./scripts](./scripts) folder
25
+
26
+
27
+ # Result
28
+
29
+ The SOLAR model is the first model <30B that can answer this question from my test:
30
+
31
+ ```
32
+ What will AI be like in the year 1010 A.D?
33
+ ```
34
+
35
+ without hullicinating into 1010 A.D is a future time (like other llama2 models)
36
+
37
+ Models greater than that, like Yi-34B could answer this paradoxic question correctly as well, since it is huge enough.
38
+
39
+ ### SOLAR 10.7B output
40
+
41
+ ![img](./assets/SOLAR.png)
42
+
43
+ ### LMCocktail 10.7B output1
44
+
45
+ ![img](./assets/SOLAR_mixed.png)
46
+
47
+ ### LMCocktail 10.7B output2
48
+
49
+ ![img](./assets/SOLAR_mixed2.png)
assets/SOLAR.png ADDED
assets/SOLAR_mixed.png ADDED
assets/SOLAR_mixed2.png ADDED
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./mixed_llm",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.36.2",
7
+ "use_cache": false
8
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5af488efed8abb6447fa3a4ff52188b92b3a7079e885d6e83b1d54686c38bb8
3
+ size 4943162240
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fca65f4755409e1bf00a55e4900535b1118d6c7832d71a43a0c3ef7193a9f2
3
+ size 4999819232
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da274d25d65e1ab0c2eb5ba0a4e3813e6f036e95d0bbe6a629fe3948e2f8d552
3
+ size 4915916080
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cdc2bb2849149d0ea095672a4ff3a45b555a2d81739701cb5afb4bcc2f3977e
3
+ size 4915916080
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d0b060ee28741a0f2ee7552a8c69b93e7907026d73490c13122ac825339814
3
+ size 1688284744
model.safetensors.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 21463048192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
395
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
396
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
397
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
398
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
399
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
400
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
405
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
406
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
407
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
408
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
409
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
410
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
411
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
412
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
413
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
414
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
415
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
416
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
417
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
419
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
420
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
421
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
422
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
423
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
424
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
425
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
426
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
427
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
428
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
429
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
430
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
431
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
432
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
433
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
434
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
435
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
436
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
437
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
438
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
440
+ "model.norm.weight": "model-00005-of-00005.safetensors"
441
+ }
442
+ }
sciprts/convert.py ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import AutoModelForCausalLM
2
+ import torch
3
+ import torch.utils.dlpack
4
+
5
+ # Load the original model
6
+ model_name = "./mixed_llm"
7
+ model = AutoModelForCausalLM.from_pretrained(model_name)
8
+
9
+ # Convert the model to a different precision
10
+ model = model.half()
11
+
12
+ # Save the model as a safetensor
13
+ model.save_pretrained(f"./mixed_llm_half", safetensors=True)
sciprts/merge.log ADDED
The diff for this file is too large to render. See raw diff
 
sciprts/merge.py ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from LM_Cocktail import mix_models_by_layers
2
+ import argparse
3
+
4
+ if __name__ == "__main__":
5
+
6
+ parser = argparse.ArgumentParser()
7
+ parser.add_argument("--model_type", type=str, default="decoder", help="Type of model to be mixed")
8
+ parser.add_argument("--output_path", type=str, default="./mixed_llm", help="Path to save the mixed model")
9
+ parser.add_argument("--max_length", type=int, default=100, help="Maximum length of the sequence to be generated")
10
+ parser.add_argument("--models", type=str, nargs='+', default=["meta-llama/Llama-2-7b-chat-hf", "Shitao/llama2-ag-news"], help="Path to the models to be mixed")
11
+ parser.add_argument("--weights", type=float, nargs='+', default=[0.7, 0.3], help="Weights of the models to be mixed")
12
+ parser.add_argument("--save_precision", type=str, default='float32', help="mixed model saved format")
13
+ args = parser.parse_args()
14
+
15
+ # Mix Large Language Models (LLMs) and save the combined model to the path: ./mixed_llm
16
+ model = mix_models_by_layers(
17
+ model_names_or_paths=args.models,
18
+ model_type=args.model_type,
19
+ weights=args.weights,
20
+ output_path=args.output_path)
21
+
22
+ print(model)
sciprts/merge.sh ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ #!/bin/bash
2
+ eval "$(conda shell.bash hook)"
3
+ conda activate llmcocktail
4
+
5
+ CUDA_VISIBLE_DEVICES=1 python merge.py \
6
+ --models /media/hangyu5/Home/Documents/Hugging-Face/LM_cocktail/meow /media/hangyu5/Home/Documents/Hugging-Face/LM_cocktail/SOLAR-10.7B-Instruct-v1.0 \
7
+ --weights 0.5 0.5 \
8
+ |& tee ./merge.log
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }