Train on more data
Browse files- README.md +3 -5
- config.json +2 -2
- model-00001-of-00005.safetensors → model-00001-of-00012.safetensors +2 -2
- model-00002-of-00005.safetensors → model-00002-of-00012.safetensors +2 -2
- model-00003-of-00005.safetensors → model-00003-of-00012.safetensors +2 -2
- model-00004-of-00005.safetensors → model-00004-of-00012.safetensors +2 -2
- model-00005-of-00005.safetensors +0 -3
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.safetensors +3 -0
- model.safetensors.index.json +435 -435
- pytorch_model-00001-of-00005.bin +1 -1
- pytorch_model-00005-of-00005.bin +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
|
|
47 |
- optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: cosine
|
49 |
- lr_scheduler_warmup_steps: 10
|
50 |
-
-
|
51 |
|
52 |
### Training Results
|
53 |
|
@@ -56,7 +56,6 @@ The following hyperparameters were used during training:
|
|
56 |
| Groups | Version | Filter | n-shot | Metric | Value | | Stderr |
|
57 |
|-------------|---------|-----------|--------|-------------|--------|-----|--------|
|
58 |
| kmmlu | N/A | none | 0 | acc | 0.3004 | ± | 0.0528 |
|
59 |
-
| | | none | 0 | acc_norm | 0.3004 | ± | 0.0528 |
|
60 |
| gsm8k | Yaml | get-answer| 5 | exact_match | 0.5625 | ± | 0.0137 |
|
61 |
| hellaswag | Yaml | none | 0 | acc | 0.6393 | ± | 0.0048 |
|
62 |
| mmlu | N/A | none | 0 | acc | 0.6305 | ± | 0.1452 |
|
@@ -67,8 +66,7 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Groups | Version | Filter | n-shot | Metric | Value | | Stderr |
|
69 |
|-------------|---------|-----------|--------|-------------|--------|-----|--------|
|
70 |
-
| kmmlu | N/A | none | 0 | acc | 0.
|
71 |
-
| | | none | 0 | acc_norm | 0.2946 | ± | 0.0496 |
|
72 |
| gsm8k | Yaml | get-answer| 5 | exact_match | 0.5527 | ± | 0.0137 |
|
73 |
| hellaswag | Yaml | none | 0 | acc | 0.6392 | ± | 0.0048 |
|
74 |
| mmlu | N/A | none | 0 | acc | 0.6303 | ± | 0.1411 |
|
@@ -80,4 +78,4 @@ The following hyperparameters were used during training:
|
|
80 |
- Transformers 4.37.0.dev0
|
81 |
- Pytorch 2.1.2+cu121
|
82 |
- Datasets 2.16.0
|
83 |
-
- Tokenizers 0.15.0
|
|
|
47 |
- optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: cosine
|
49 |
- lr_scheduler_warmup_steps: 10
|
50 |
+
- num_epochs: 1
|
51 |
|
52 |
### Training Results
|
53 |
|
|
|
56 |
| Groups | Version | Filter | n-shot | Metric | Value | | Stderr |
|
57 |
|-------------|---------|-----------|--------|-------------|--------|-----|--------|
|
58 |
| kmmlu | N/A | none | 0 | acc | 0.3004 | ± | 0.0528 |
|
|
|
59 |
| gsm8k | Yaml | get-answer| 5 | exact_match | 0.5625 | ± | 0.0137 |
|
60 |
| hellaswag | Yaml | none | 0 | acc | 0.6393 | ± | 0.0048 |
|
61 |
| mmlu | N/A | none | 0 | acc | 0.6305 | ± | 0.1452 |
|
|
|
66 |
|
67 |
| Groups | Version | Filter | n-shot | Metric | Value | | Stderr |
|
68 |
|-------------|---------|-----------|--------|-------------|--------|-----|--------|
|
69 |
+
| kmmlu | N/A | none | 0 | acc | 0.2948 | ± | 0.0537 |
|
|
|
70 |
| gsm8k | Yaml | get-answer| 5 | exact_match | 0.5527 | ± | 0.0137 |
|
71 |
| hellaswag | Yaml | none | 0 | acc | 0.6392 | ± | 0.0048 |
|
72 |
| mmlu | N/A | none | 0 | acc | 0.6303 | ± | 0.1411 |
|
|
|
78 |
- Transformers 4.37.0.dev0
|
79 |
- Pytorch 2.1.2+cu121
|
80 |
- Datasets 2.16.0
|
81 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -21,7 +21,7 @@
|
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
-
"torch_dtype": "
|
25 |
"transformers_version": "4.37.0.dev0",
|
26 |
"use_cache": false,
|
27 |
"vocab_size": 48000
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "seungduk/KoSOLAR-10.7B-v0.1",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
"transformers_version": "4.37.0.dev0",
|
26 |
"use_cache": false,
|
27 |
"vocab_size": 48000
|
model-00001-of-00005.safetensors → model-00001-of-00012.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0ae8ac5865ae8ca26224c249b7c83d671f1f9b5c4f3c0478861e67ea63bad48
|
3 |
+
size 1903218384
|
model-00002-of-00005.safetensors → model-00002-of-00012.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53000e1bfd1396a50cac2f27d8a162484e3f7f5f27fb7ce95ad00f42075294d1
|
3 |
+
size 1979797984
|
model-00003-of-00005.safetensors → model-00003-of-00012.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55f9865fdb5aaa4faf5d49b449a89d3a935e8179f2dc9b498fe1a3701a3ee63c
|
3 |
+
size 1946227312
|
model-00004-of-00005.safetensors → model-00004-of-00012.safetensors
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc076d4133a17ff2d3531a8e6667c0537febfe5488b989b7af1abdcfa830ae63
|
3 |
+
size 1979798024
|
model-00005-of-00005.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a646fd121dcc5933a4a77468b814a4a8adad35093f6c9c7f81fb4d29b77b1ce9
|
3 |
-
size 1936797416
|
|
|
|
|
|
|
|
model-00005-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bd23fd11114e0e6033d45cd47c6371f7e08e82b9545adb2375af081480380e5
|
3 |
+
size 1946227328
|
model-00006-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a34c297dc5cb8c69d9edaf974804fb7bea5a66fa5e9be140ca30335a4168b38
|
3 |
+
size 1979798024
|
model-00007-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23b8a30ce5ba7ae3ff7529298ef929e9caebdde74bde80cfb087b9482a3e1039
|
3 |
+
size 1946227328
|
model-00008-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d38c8fe99ecfeda8887ccdc4fdfc212d67cb3f23c787d7232aa0401680e3f11c
|
3 |
+
size 1979798024
|
model-00009-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e0e142d0db2a112fe87930cb1de2fb74c205079e437984f6731ff6543224939
|
3 |
+
size 1946227328
|
model-00010-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236aca1fbe91160048003d21334ed9cb4aa3aeec83531dd28bd24b2efb09fc47
|
3 |
+
size 1979798024
|
model-00011-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:872fe8cf4ee3289af57c88406f63d9c0e121836f1db7f2099f752fb8d7c69b80
|
3 |
+
size 1744908432
|
model-00012-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c03284af99d00cf767081e67f2fd54d8b52ddd23245f99569e97e67e98df39d
|
3 |
+
size 393216128
|
model.safetensors.index.json
CHANGED
@@ -3,440 +3,440 @@
|
|
3 |
"total_size": 21725192192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"lm_head.weight": "model-
|
7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
15 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
16 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
17 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
21 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
22 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
23 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
24 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
25 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
26 |
-
"model.layers.10.input_layernorm.weight": "model-
|
27 |
-
"model.layers.10.mlp.down_proj.weight": "model-
|
28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
29 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
30 |
-
"model.layers.10.post_attention_layernorm.weight": "model-
|
31 |
-
"model.layers.10.self_attn.k_proj.weight": "model-
|
32 |
-
"model.layers.10.self_attn.o_proj.weight": "model-
|
33 |
-
"model.layers.10.self_attn.q_proj.weight": "model-
|
34 |
-
"model.layers.10.self_attn.v_proj.weight": "model-
|
35 |
-
"model.layers.11.input_layernorm.weight": "model-
|
36 |
-
"model.layers.11.mlp.down_proj.weight": "model-
|
37 |
-
"model.layers.11.mlp.gate_proj.weight": "model-
|
38 |
-
"model.layers.11.mlp.up_proj.weight": "model-
|
39 |
-
"model.layers.11.post_attention_layernorm.weight": "model-
|
40 |
-
"model.layers.11.self_attn.k_proj.weight": "model-
|
41 |
-
"model.layers.11.self_attn.o_proj.weight": "model-
|
42 |
-
"model.layers.11.self_attn.q_proj.weight": "model-
|
43 |
-
"model.layers.11.self_attn.v_proj.weight": "model-
|
44 |
-
"model.layers.12.input_layernorm.weight": "model-
|
45 |
-
"model.layers.12.mlp.down_proj.weight": "model-
|
46 |
-
"model.layers.12.mlp.gate_proj.weight": "model-
|
47 |
-
"model.layers.12.mlp.up_proj.weight": "model-
|
48 |
-
"model.layers.12.post_attention_layernorm.weight": "model-
|
49 |
-
"model.layers.12.self_attn.k_proj.weight": "model-
|
50 |
-
"model.layers.12.self_attn.o_proj.weight": "model-
|
51 |
-
"model.layers.12.self_attn.q_proj.weight": "model-
|
52 |
-
"model.layers.12.self_attn.v_proj.weight": "model-
|
53 |
-
"model.layers.13.input_layernorm.weight": "model-
|
54 |
-
"model.layers.13.mlp.down_proj.weight": "model-
|
55 |
-
"model.layers.13.mlp.gate_proj.weight": "model-
|
56 |
-
"model.layers.13.mlp.up_proj.weight": "model-
|
57 |
-
"model.layers.13.post_attention_layernorm.weight": "model-
|
58 |
-
"model.layers.13.self_attn.k_proj.weight": "model-
|
59 |
-
"model.layers.13.self_attn.o_proj.weight": "model-
|
60 |
-
"model.layers.13.self_attn.q_proj.weight": "model-
|
61 |
-
"model.layers.13.self_attn.v_proj.weight": "model-
|
62 |
-
"model.layers.14.input_layernorm.weight": "model-
|
63 |
-
"model.layers.14.mlp.down_proj.weight": "model-
|
64 |
-
"model.layers.14.mlp.gate_proj.weight": "model-
|
65 |
-
"model.layers.14.mlp.up_proj.weight": "model-
|
66 |
-
"model.layers.14.post_attention_layernorm.weight": "model-
|
67 |
-
"model.layers.14.self_attn.k_proj.weight": "model-
|
68 |
-
"model.layers.14.self_attn.o_proj.weight": "model-
|
69 |
-
"model.layers.14.self_attn.q_proj.weight": "model-
|
70 |
-
"model.layers.14.self_attn.v_proj.weight": "model-
|
71 |
-
"model.layers.15.input_layernorm.weight": "model-
|
72 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
73 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
74 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
76 |
-
"model.layers.15.self_attn.k_proj.weight": "model-
|
77 |
-
"model.layers.15.self_attn.o_proj.weight": "model-
|
78 |
-
"model.layers.15.self_attn.q_proj.weight": "model-
|
79 |
-
"model.layers.15.self_attn.v_proj.weight": "model-
|
80 |
-
"model.layers.16.input_layernorm.weight": "model-
|
81 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
83 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
89 |
-
"model.layers.17.input_layernorm.weight": "model-
|
90 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
92 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
98 |
-
"model.layers.18.input_layernorm.weight": "model-
|
99 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
101 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
107 |
-
"model.layers.19.input_layernorm.weight": "model-
|
108 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
110 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-
|
113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-
|
115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-
|
116 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
117 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
118 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
119 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
120 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
121 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
122 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
123 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
124 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-
|
128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
134 |
-
"model.layers.21.input_layernorm.weight": "model-
|
135 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
136 |
-
"model.layers.21.mlp.gate_proj.weight": "model-
|
137 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-
|
140 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
142 |
-
"model.layers.21.self_attn.v_proj.weight": "model-
|
143 |
-
"model.layers.22.input_layernorm.weight": "model-
|
144 |
-
"model.layers.22.mlp.down_proj.weight": "model-
|
145 |
-
"model.layers.22.mlp.gate_proj.weight": "model-
|
146 |
-
"model.layers.22.mlp.up_proj.weight": "model-
|
147 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
152 |
-
"model.layers.23.input_layernorm.weight": "model-
|
153 |
-
"model.layers.23.mlp.down_proj.weight": "model-
|
154 |
-
"model.layers.23.mlp.gate_proj.weight": "model-
|
155 |
-
"model.layers.23.mlp.up_proj.weight": "model-
|
156 |
-
"model.layers.23.post_attention_layernorm.weight": "model-
|
157 |
-
"model.layers.23.self_attn.k_proj.weight": "model-
|
158 |
-
"model.layers.23.self_attn.o_proj.weight": "model-
|
159 |
-
"model.layers.23.self_attn.q_proj.weight": "model-
|
160 |
-
"model.layers.23.self_attn.v_proj.weight": "model-
|
161 |
-
"model.layers.24.input_layernorm.weight": "model-
|
162 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
163 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
164 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
165 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
166 |
-
"model.layers.24.self_attn.k_proj.weight": "model-
|
167 |
-
"model.layers.24.self_attn.o_proj.weight": "model-
|
168 |
-
"model.layers.24.self_attn.q_proj.weight": "model-
|
169 |
-
"model.layers.24.self_attn.v_proj.weight": "model-
|
170 |
-
"model.layers.25.input_layernorm.weight": "model-
|
171 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
172 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
173 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
174 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
175 |
-
"model.layers.25.self_attn.k_proj.weight": "model-
|
176 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
177 |
-
"model.layers.25.self_attn.q_proj.weight": "model-
|
178 |
-
"model.layers.25.self_attn.v_proj.weight": "model-
|
179 |
-
"model.layers.26.input_layernorm.weight": "model-
|
180 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
181 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
182 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
183 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
184 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
185 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
186 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
187 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
188 |
-
"model.layers.27.input_layernorm.weight": "model-
|
189 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
191 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
192 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
193 |
-
"model.layers.27.self_attn.k_proj.weight": "model-
|
194 |
-
"model.layers.27.self_attn.o_proj.weight": "model-
|
195 |
-
"model.layers.27.self_attn.q_proj.weight": "model-
|
196 |
-
"model.layers.27.self_attn.v_proj.weight": "model-
|
197 |
-
"model.layers.28.input_layernorm.weight": "model-
|
198 |
-
"model.layers.28.mlp.down_proj.weight": "model-
|
199 |
-
"model.layers.28.mlp.gate_proj.weight": "model-
|
200 |
-
"model.layers.28.mlp.up_proj.weight": "model-
|
201 |
-
"model.layers.28.post_attention_layernorm.weight": "model-
|
202 |
-
"model.layers.28.self_attn.k_proj.weight": "model-
|
203 |
-
"model.layers.28.self_attn.o_proj.weight": "model-
|
204 |
-
"model.layers.28.self_attn.q_proj.weight": "model-
|
205 |
-
"model.layers.28.self_attn.v_proj.weight": "model-
|
206 |
-
"model.layers.29.input_layernorm.weight": "model-
|
207 |
-
"model.layers.29.mlp.down_proj.weight": "model-
|
208 |
-
"model.layers.29.mlp.gate_proj.weight": "model-
|
209 |
-
"model.layers.29.mlp.up_proj.weight": "model-
|
210 |
-
"model.layers.29.post_attention_layernorm.weight": "model-
|
211 |
-
"model.layers.29.self_attn.k_proj.weight": "model-
|
212 |
-
"model.layers.29.self_attn.o_proj.weight": "model-
|
213 |
-
"model.layers.29.self_attn.q_proj.weight": "model-
|
214 |
-
"model.layers.29.self_attn.v_proj.weight": "model-
|
215 |
-
"model.layers.3.input_layernorm.weight": "model-
|
216 |
-
"model.layers.3.mlp.down_proj.weight": "model-
|
217 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
218 |
-
"model.layers.3.mlp.up_proj.weight": "model-
|
219 |
-
"model.layers.3.post_attention_layernorm.weight": "model-
|
220 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
221 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
222 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
223 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-
|
224 |
-
"model.layers.30.input_layernorm.weight": "model-
|
225 |
-
"model.layers.30.mlp.down_proj.weight": "model-
|
226 |
-
"model.layers.30.mlp.gate_proj.weight": "model-
|
227 |
-
"model.layers.30.mlp.up_proj.weight": "model-
|
228 |
-
"model.layers.30.post_attention_layernorm.weight": "model-
|
229 |
-
"model.layers.30.self_attn.k_proj.weight": "model-
|
230 |
-
"model.layers.30.self_attn.o_proj.weight": "model-
|
231 |
-
"model.layers.30.self_attn.q_proj.weight": "model-
|
232 |
-
"model.layers.30.self_attn.v_proj.weight": "model-
|
233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
235 |
-
"model.layers.31.mlp.gate_proj.weight": "model-
|
236 |
-
"model.layers.31.mlp.up_proj.weight": "model-
|
237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
238 |
-
"model.layers.31.self_attn.k_proj.weight": "model-
|
239 |
-
"model.layers.31.self_attn.o_proj.weight": "model-
|
240 |
-
"model.layers.31.self_attn.q_proj.weight": "model-
|
241 |
-
"model.layers.31.self_attn.v_proj.weight": "model-
|
242 |
-
"model.layers.32.input_layernorm.weight": "model-
|
243 |
-
"model.layers.32.mlp.down_proj.weight": "model-
|
244 |
-
"model.layers.32.mlp.gate_proj.weight": "model-
|
245 |
-
"model.layers.32.mlp.up_proj.weight": "model-
|
246 |
-
"model.layers.32.post_attention_layernorm.weight": "model-
|
247 |
-
"model.layers.32.self_attn.k_proj.weight": "model-
|
248 |
-
"model.layers.32.self_attn.o_proj.weight": "model-
|
249 |
-
"model.layers.32.self_attn.q_proj.weight": "model-
|
250 |
-
"model.layers.32.self_attn.v_proj.weight": "model-
|
251 |
-
"model.layers.33.input_layernorm.weight": "model-
|
252 |
-
"model.layers.33.mlp.down_proj.weight": "model-
|
253 |
-
"model.layers.33.mlp.gate_proj.weight": "model-
|
254 |
-
"model.layers.33.mlp.up_proj.weight": "model-
|
255 |
-
"model.layers.33.post_attention_layernorm.weight": "model-
|
256 |
-
"model.layers.33.self_attn.k_proj.weight": "model-
|
257 |
-
"model.layers.33.self_attn.o_proj.weight": "model-
|
258 |
-
"model.layers.33.self_attn.q_proj.weight": "model-
|
259 |
-
"model.layers.33.self_attn.v_proj.weight": "model-
|
260 |
-
"model.layers.34.input_layernorm.weight": "model-
|
261 |
-
"model.layers.34.mlp.down_proj.weight": "model-
|
262 |
-
"model.layers.34.mlp.gate_proj.weight": "model-
|
263 |
-
"model.layers.34.mlp.up_proj.weight": "model-
|
264 |
-
"model.layers.34.post_attention_layernorm.weight": "model-
|
265 |
-
"model.layers.34.self_attn.k_proj.weight": "model-
|
266 |
-
"model.layers.34.self_attn.o_proj.weight": "model-
|
267 |
-
"model.layers.34.self_attn.q_proj.weight": "model-
|
268 |
-
"model.layers.34.self_attn.v_proj.weight": "model-
|
269 |
-
"model.layers.35.input_layernorm.weight": "model-
|
270 |
-
"model.layers.35.mlp.down_proj.weight": "model-
|
271 |
-
"model.layers.35.mlp.gate_proj.weight": "model-
|
272 |
-
"model.layers.35.mlp.up_proj.weight": "model-
|
273 |
-
"model.layers.35.post_attention_layernorm.weight": "model-
|
274 |
-
"model.layers.35.self_attn.k_proj.weight": "model-
|
275 |
-
"model.layers.35.self_attn.o_proj.weight": "model-
|
276 |
-
"model.layers.35.self_attn.q_proj.weight": "model-
|
277 |
-
"model.layers.35.self_attn.v_proj.weight": "model-
|
278 |
-
"model.layers.36.input_layernorm.weight": "model-
|
279 |
-
"model.layers.36.mlp.down_proj.weight": "model-
|
280 |
-
"model.layers.36.mlp.gate_proj.weight": "model-
|
281 |
-
"model.layers.36.mlp.up_proj.weight": "model-
|
282 |
-
"model.layers.36.post_attention_layernorm.weight": "model-
|
283 |
-
"model.layers.36.self_attn.k_proj.weight": "model-
|
284 |
-
"model.layers.36.self_attn.o_proj.weight": "model-
|
285 |
-
"model.layers.36.self_attn.q_proj.weight": "model-
|
286 |
-
"model.layers.36.self_attn.v_proj.weight": "model-
|
287 |
-
"model.layers.37.input_layernorm.weight": "model-
|
288 |
-
"model.layers.37.mlp.down_proj.weight": "model-
|
289 |
-
"model.layers.37.mlp.gate_proj.weight": "model-
|
290 |
-
"model.layers.37.mlp.up_proj.weight": "model-
|
291 |
-
"model.layers.37.post_attention_layernorm.weight": "model-
|
292 |
-
"model.layers.37.self_attn.k_proj.weight": "model-
|
293 |
-
"model.layers.37.self_attn.o_proj.weight": "model-
|
294 |
-
"model.layers.37.self_attn.q_proj.weight": "model-
|
295 |
-
"model.layers.37.self_attn.v_proj.weight": "model-
|
296 |
-
"model.layers.38.input_layernorm.weight": "model-
|
297 |
-
"model.layers.38.mlp.down_proj.weight": "model-
|
298 |
-
"model.layers.38.mlp.gate_proj.weight": "model-
|
299 |
-
"model.layers.38.mlp.up_proj.weight": "model-
|
300 |
-
"model.layers.38.post_attention_layernorm.weight": "model-
|
301 |
-
"model.layers.38.self_attn.k_proj.weight": "model-
|
302 |
-
"model.layers.38.self_attn.o_proj.weight": "model-
|
303 |
-
"model.layers.38.self_attn.q_proj.weight": "model-
|
304 |
-
"model.layers.38.self_attn.v_proj.weight": "model-
|
305 |
-
"model.layers.39.input_layernorm.weight": "model-
|
306 |
-
"model.layers.39.mlp.down_proj.weight": "model-
|
307 |
-
"model.layers.39.mlp.gate_proj.weight": "model-
|
308 |
-
"model.layers.39.mlp.up_proj.weight": "model-
|
309 |
-
"model.layers.39.post_attention_layernorm.weight": "model-
|
310 |
-
"model.layers.39.self_attn.k_proj.weight": "model-
|
311 |
-
"model.layers.39.self_attn.o_proj.weight": "model-
|
312 |
-
"model.layers.39.self_attn.q_proj.weight": "model-
|
313 |
-
"model.layers.39.self_attn.v_proj.weight": "model-
|
314 |
-
"model.layers.4.input_layernorm.weight": "model-
|
315 |
-
"model.layers.4.mlp.down_proj.weight": "model-
|
316 |
-
"model.layers.4.mlp.gate_proj.weight": "model-
|
317 |
-
"model.layers.4.mlp.up_proj.weight": "model-
|
318 |
-
"model.layers.4.post_attention_layernorm.weight": "model-
|
319 |
-
"model.layers.4.self_attn.k_proj.weight": "model-
|
320 |
-
"model.layers.4.self_attn.o_proj.weight": "model-
|
321 |
-
"model.layers.4.self_attn.q_proj.weight": "model-
|
322 |
-
"model.layers.4.self_attn.v_proj.weight": "model-
|
323 |
-
"model.layers.40.input_layernorm.weight": "model-
|
324 |
-
"model.layers.40.mlp.down_proj.weight": "model-
|
325 |
-
"model.layers.40.mlp.gate_proj.weight": "model-
|
326 |
-
"model.layers.40.mlp.up_proj.weight": "model-
|
327 |
-
"model.layers.40.post_attention_layernorm.weight": "model-
|
328 |
-
"model.layers.40.self_attn.k_proj.weight": "model-
|
329 |
-
"model.layers.40.self_attn.o_proj.weight": "model-
|
330 |
-
"model.layers.40.self_attn.q_proj.weight": "model-
|
331 |
-
"model.layers.40.self_attn.v_proj.weight": "model-
|
332 |
-
"model.layers.41.input_layernorm.weight": "model-
|
333 |
-
"model.layers.41.mlp.down_proj.weight": "model-
|
334 |
-
"model.layers.41.mlp.gate_proj.weight": "model-
|
335 |
-
"model.layers.41.mlp.up_proj.weight": "model-
|
336 |
-
"model.layers.41.post_attention_layernorm.weight": "model-
|
337 |
-
"model.layers.41.self_attn.k_proj.weight": "model-
|
338 |
-
"model.layers.41.self_attn.o_proj.weight": "model-
|
339 |
-
"model.layers.41.self_attn.q_proj.weight": "model-
|
340 |
-
"model.layers.41.self_attn.v_proj.weight": "model-
|
341 |
-
"model.layers.42.input_layernorm.weight": "model-
|
342 |
-
"model.layers.42.mlp.down_proj.weight": "model-
|
343 |
-
"model.layers.42.mlp.gate_proj.weight": "model-
|
344 |
-
"model.layers.42.mlp.up_proj.weight": "model-
|
345 |
-
"model.layers.42.post_attention_layernorm.weight": "model-
|
346 |
-
"model.layers.42.self_attn.k_proj.weight": "model-
|
347 |
-
"model.layers.42.self_attn.o_proj.weight": "model-
|
348 |
-
"model.layers.42.self_attn.q_proj.weight": "model-
|
349 |
-
"model.layers.42.self_attn.v_proj.weight": "model-
|
350 |
-
"model.layers.43.input_layernorm.weight": "model-
|
351 |
-
"model.layers.43.mlp.down_proj.weight": "model-
|
352 |
-
"model.layers.43.mlp.gate_proj.weight": "model-
|
353 |
-
"model.layers.43.mlp.up_proj.weight": "model-
|
354 |
-
"model.layers.43.post_attention_layernorm.weight": "model-
|
355 |
-
"model.layers.43.self_attn.k_proj.weight": "model-
|
356 |
-
"model.layers.43.self_attn.o_proj.weight": "model-
|
357 |
-
"model.layers.43.self_attn.q_proj.weight": "model-
|
358 |
-
"model.layers.43.self_attn.v_proj.weight": "model-
|
359 |
-
"model.layers.44.input_layernorm.weight": "model-
|
360 |
-
"model.layers.44.mlp.down_proj.weight": "model-
|
361 |
-
"model.layers.44.mlp.gate_proj.weight": "model-
|
362 |
-
"model.layers.44.mlp.up_proj.weight": "model-
|
363 |
-
"model.layers.44.post_attention_layernorm.weight": "model-
|
364 |
-
"model.layers.44.self_attn.k_proj.weight": "model-
|
365 |
-
"model.layers.44.self_attn.o_proj.weight": "model-
|
366 |
-
"model.layers.44.self_attn.q_proj.weight": "model-
|
367 |
-
"model.layers.44.self_attn.v_proj.weight": "model-
|
368 |
-
"model.layers.45.input_layernorm.weight": "model-
|
369 |
-
"model.layers.45.mlp.down_proj.weight": "model-
|
370 |
-
"model.layers.45.mlp.gate_proj.weight": "model-
|
371 |
-
"model.layers.45.mlp.up_proj.weight": "model-
|
372 |
-
"model.layers.45.post_attention_layernorm.weight": "model-
|
373 |
-
"model.layers.45.self_attn.k_proj.weight": "model-
|
374 |
-
"model.layers.45.self_attn.o_proj.weight": "model-
|
375 |
-
"model.layers.45.self_attn.q_proj.weight": "model-
|
376 |
-
"model.layers.45.self_attn.v_proj.weight": "model-
|
377 |
-
"model.layers.46.input_layernorm.weight": "model-
|
378 |
-
"model.layers.46.mlp.down_proj.weight": "model-
|
379 |
-
"model.layers.46.mlp.gate_proj.weight": "model-
|
380 |
-
"model.layers.46.mlp.up_proj.weight": "model-
|
381 |
-
"model.layers.46.post_attention_layernorm.weight": "model-
|
382 |
-
"model.layers.46.self_attn.k_proj.weight": "model-
|
383 |
-
"model.layers.46.self_attn.o_proj.weight": "model-
|
384 |
-
"model.layers.46.self_attn.q_proj.weight": "model-
|
385 |
-
"model.layers.46.self_attn.v_proj.weight": "model-
|
386 |
-
"model.layers.47.input_layernorm.weight": "model-
|
387 |
-
"model.layers.47.mlp.down_proj.weight": "model-
|
388 |
-
"model.layers.47.mlp.gate_proj.weight": "model-
|
389 |
-
"model.layers.47.mlp.up_proj.weight": "model-
|
390 |
-
"model.layers.47.post_attention_layernorm.weight": "model-
|
391 |
-
"model.layers.47.self_attn.k_proj.weight": "model-
|
392 |
-
"model.layers.47.self_attn.o_proj.weight": "model-
|
393 |
-
"model.layers.47.self_attn.q_proj.weight": "model-
|
394 |
-
"model.layers.47.self_attn.v_proj.weight": "model-
|
395 |
-
"model.layers.5.input_layernorm.weight": "model-
|
396 |
-
"model.layers.5.mlp.down_proj.weight": "model-
|
397 |
-
"model.layers.5.mlp.gate_proj.weight": "model-
|
398 |
-
"model.layers.5.mlp.up_proj.weight": "model-
|
399 |
-
"model.layers.5.post_attention_layernorm.weight": "model-
|
400 |
-
"model.layers.5.self_attn.k_proj.weight": "model-
|
401 |
-
"model.layers.5.self_attn.o_proj.weight": "model-
|
402 |
-
"model.layers.5.self_attn.q_proj.weight": "model-
|
403 |
-
"model.layers.5.self_attn.v_proj.weight": "model-
|
404 |
-
"model.layers.6.input_layernorm.weight": "model-
|
405 |
-
"model.layers.6.mlp.down_proj.weight": "model-
|
406 |
-
"model.layers.6.mlp.gate_proj.weight": "model-
|
407 |
-
"model.layers.6.mlp.up_proj.weight": "model-
|
408 |
-
"model.layers.6.post_attention_layernorm.weight": "model-
|
409 |
-
"model.layers.6.self_attn.k_proj.weight": "model-
|
410 |
-
"model.layers.6.self_attn.o_proj.weight": "model-
|
411 |
-
"model.layers.6.self_attn.q_proj.weight": "model-
|
412 |
-
"model.layers.6.self_attn.v_proj.weight": "model-
|
413 |
-
"model.layers.7.input_layernorm.weight": "model-
|
414 |
-
"model.layers.7.mlp.down_proj.weight": "model-
|
415 |
-
"model.layers.7.mlp.gate_proj.weight": "model-
|
416 |
-
"model.layers.7.mlp.up_proj.weight": "model-
|
417 |
-
"model.layers.7.post_attention_layernorm.weight": "model-
|
418 |
-
"model.layers.7.self_attn.k_proj.weight": "model-
|
419 |
-
"model.layers.7.self_attn.o_proj.weight": "model-
|
420 |
-
"model.layers.7.self_attn.q_proj.weight": "model-
|
421 |
-
"model.layers.7.self_attn.v_proj.weight": "model-
|
422 |
-
"model.layers.8.input_layernorm.weight": "model-
|
423 |
-
"model.layers.8.mlp.down_proj.weight": "model-
|
424 |
-
"model.layers.8.mlp.gate_proj.weight": "model-
|
425 |
-
"model.layers.8.mlp.up_proj.weight": "model-
|
426 |
-
"model.layers.8.post_attention_layernorm.weight": "model-
|
427 |
-
"model.layers.8.self_attn.k_proj.weight": "model-
|
428 |
-
"model.layers.8.self_attn.o_proj.weight": "model-
|
429 |
-
"model.layers.8.self_attn.q_proj.weight": "model-
|
430 |
-
"model.layers.8.self_attn.v_proj.weight": "model-
|
431 |
-
"model.layers.9.input_layernorm.weight": "model-
|
432 |
-
"model.layers.9.mlp.down_proj.weight": "model-
|
433 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
434 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
435 |
-
"model.layers.9.post_attention_layernorm.weight": "model-
|
436 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
437 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
438 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
439 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
440 |
-
"model.norm.weight": "model-
|
441 |
}
|
442 |
}
|
|
|
3 |
"total_size": 21725192192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00012-of-00012.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00012.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
242 |
+
"model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
251 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
260 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
269 |
+
"model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
278 |
+
"model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
287 |
+
"model.layers.37.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
296 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
305 |
+
"model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
314 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
323 |
+
"model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
324 |
+
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
325 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
326 |
+
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
327 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
328 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
329 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
330 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
331 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
332 |
+
"model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
333 |
+
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
334 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
335 |
+
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
336 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
337 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
338 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
339 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
340 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
341 |
+
"model.layers.42.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
342 |
+
"model.layers.42.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
343 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
344 |
+
"model.layers.42.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
345 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
346 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
347 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
348 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
349 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
350 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
351 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
352 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
353 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
354 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
355 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
356 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
357 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
358 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
359 |
+
"model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
361 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
362 |
+
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
364 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
365 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
366 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
367 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
368 |
+
"model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
369 |
+
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
370 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
371 |
+
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
372 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
374 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
377 |
+
"model.layers.46.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
378 |
+
"model.layers.46.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
379 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
380 |
+
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
381 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
382 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
383 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
384 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
385 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
386 |
+
"model.layers.47.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
387 |
+
"model.layers.47.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
388 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
389 |
+
"model.layers.47.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
390 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
391 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
392 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
393 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
394 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
395 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
396 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
397 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
398 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
399 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
400 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
401 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
402 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
403 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
404 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
405 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
406 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
407 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
408 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
409 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
410 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
411 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
412 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
413 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
414 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
415 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
416 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
417 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
418 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
|
419 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
|
420 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
|
421 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
|
422 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
423 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
424 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
425 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
426 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
427 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
428 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
429 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
430 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
431 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
432 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
433 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
434 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
435 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
436 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
437 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
440 |
+
"model.norm.weight": "model-00011-of-00012.safetensors"
|
441 |
}
|
442 |
}
|
pytorch_model-00001-of-00005.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4956816866
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:858849843f69e1bb65ec13b80a4c3a8a514085467bc7fd5eb2f5b0d5cdea86db
|
3 |
size 4956816866
|
pytorch_model-00005-of-00005.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1936805500
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d379580f8b63c860e8b958539e94bff62f16b7aa7d6e88aa837595c1b90ec20f
|
3 |
size 1936805500
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
-
"special":
|
36 |
},
|
37 |
"32001": {
|
38 |
"content": "<|im_start|>",
|
|
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
+
"special": true
|
36 |
},
|
37 |
"32001": {
|
38 |
"content": "<|im_start|>",
|