Commit
•
b779fb2
1
Parent(s):
78d2e3f
Upload GemmaForCausalLM
Browse files- README.md +1 -0
- config.json +28 -0
- generation_config.json +7 -0
- model-00001-of-00018.safetensors +3 -0
- model-00002-of-00018.safetensors +3 -0
- model-00003-of-00018.safetensors +3 -0
- model-00004-of-00018.safetensors +3 -0
- model-00005-of-00018.safetensors +3 -0
- model-00006-of-00018.safetensors +3 -0
- model-00007-of-00018.safetensors +3 -0
- model-00008-of-00018.safetensors +3 -0
- model-00009-of-00018.safetensors +3 -0
- model-00010-of-00018.safetensors +3 -0
- model-00011-of-00018.safetensors +3 -0
- model-00012-of-00018.safetensors +3 -0
- model-00013-of-00018.safetensors +3 -0
- model-00014-of-00018.safetensors +3 -0
- model-00015-of-00018.safetensors +3 -0
- model-00016-of-00018.safetensors +3 -0
- model-00017-of-00018.safetensors +3 -0
- model-00018-of-00018.safetensors +3 -0
- model.safetensors.index.json +261 -0
README.md
CHANGED
@@ -3,6 +3,7 @@ license: apache-2.0
|
|
3 |
library_name: adapter-transformers
|
4 |
tags:
|
5 |
- medical
|
|
|
6 |
---
|
7 |
# Model Card for Model ID
|
8 |
|
|
|
3 |
library_name: adapter-transformers
|
4 |
tags:
|
5 |
- medical
|
6 |
+
- llama-factory
|
7 |
---
|
8 |
# Model Card for Model ID
|
9 |
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/gemma-1.1-7b-it",
|
3 |
+
"architectures": [
|
4 |
+
"GemmaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "gelu_pytorch_tanh",
|
12 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
13 |
+
"hidden_size": 3072,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 24576,
|
16 |
+
"max_position_embeddings": 8192,
|
17 |
+
"model_type": "gemma",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 28,
|
20 |
+
"num_key_value_heads": 16,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.41.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 256000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
+
}
|
model-00001-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:602d61323989ba73dd85ad6698bcc1d512d15ab431fa878ca190d6870caa17f2
|
3 |
+
size 1572864144
|
model-00002-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb653c43fe247a60a5068f253af89f4e8e8ceb835e654aef7cdea6853f453f09
|
3 |
+
size 956315336
|
model-00003-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f679feba81be554356a9cbb0b7d6f9d867fdac978d21d9bf0021f9af50fca041
|
3 |
+
size 956327848
|
model-00004-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55134146c2637ff027510e8edd3a78afef09879580b4a7f778e48d738b4909c8
|
3 |
+
size 956327848
|
model-00005-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47ce7e4192b064d1474ea1ac5da9bac28e91d223dc7d4780ad3f7d1b89bf779
|
3 |
+
size 855651576
|
model-00006-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e60839f20a68b9047501c3292530d55d876555bfa167d6d24ec720f00f88386d
|
3 |
+
size 956327848
|
model-00007-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7150daddf20475ee7ed44221720011746a92f7f778e4d2f5159025e9509fbce5
|
3 |
+
size 956327856
|
model-00008-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4750d71d0c6ea33d6805e19e12006b729c1bd083a245e12dbafeaddd1f7bbe3
|
3 |
+
size 855651592
|
model-00009-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e56f09f6d4bf8cc60dfbb12d407e47b6b4fa166435f9441b1221d72d03d63b36
|
3 |
+
size 956327864
|
model-00010-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2fcd02e9f3245dd0c975dcc084b7195af040538e1c11b754df12ee6c6e56829
|
3 |
+
size 956327864
|
model-00011-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19eaf0aec56ce9eb9624ea9a97e33eb5ff6e8d65878f2e219fea07c7fd91c3a5
|
3 |
+
size 855651592
|
model-00012-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d767c46cc4181d04f7da59a09d7445e15df141bffa09fce887b1ec177c5629
|
3 |
+
size 956327864
|
model-00013-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5657857a0aaaba07ccd475ea52664abaa45cf107853712b932dc2fa2198cbcb
|
3 |
+
size 956327864
|
model-00014-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2e2e3c6f1bbd13c15c1334a58e4f47d1160abacc0dd6a9438a8dd571df2687e
|
3 |
+
size 855651592
|
model-00015-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5f7ba8c5cd24a50396fa7b21622ba474008cb241a3da0cd3228baeda36e2f0d
|
3 |
+
size 956327864
|
model-00016-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab0b2fe968285035e3339c0678b8b5cecc6ab56a15e9f41986bf32431856576
|
3 |
+
size 956327864
|
model-00017-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37a7560a359c6a399fd894527c84fcfb3bcfda4000e8f4acb097a832dbd9e013
|
3 |
+
size 855651592
|
model-00018-of-00018.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7655fe1cdbbc3df7e407cfc9fc4ce84585103032c55b825d7b38908d0bc1683a
|
3 |
+
size 704675280
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 17075361792
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00018.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
16 |
+
"model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
|
20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
|
22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
|
25 |
+
"model.layers.10.input_layernorm.weight": "model-00008-of-00018.safetensors",
|
26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
34 |
+
"model.layers.11.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
|
38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
|
40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
|
43 |
+
"model.layers.12.input_layernorm.weight": "model-00009-of-00018.safetensors",
|
44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
|
47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
52 |
+
"model.layers.13.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
|
58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
|
61 |
+
"model.layers.14.input_layernorm.weight": "model-00010-of-00018.safetensors",
|
62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
|
65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
70 |
+
"model.layers.15.input_layernorm.weight": "model-00011-of-00018.safetensors",
|
71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
|
76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
|
79 |
+
"model.layers.16.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
|
83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
|
85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00012-of-00018.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
97 |
+
"model.layers.18.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
|
100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
|
103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
|
104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
|
105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
|
106 |
+
"model.layers.19.input_layernorm.weight": "model-00013-of-00018.safetensors",
|
107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
|
108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
|
109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
|
110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
|
111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
115 |
+
"model.layers.2.input_layernorm.weight": "model-00003-of-00018.safetensors",
|
116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
|
117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
|
119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
|
120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
124 |
+
"model.layers.20.input_layernorm.weight": "model-00014-of-00018.safetensors",
|
125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
|
126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
|
129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
|
130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
|
131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
|
132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
|
133 |
+
"model.layers.21.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
|
136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
|
137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
|
139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
|
140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
|
141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
|
142 |
+
"model.layers.22.input_layernorm.weight": "model-00015-of-00018.safetensors",
|
143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
|
144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
|
146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
|
147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
151 |
+
"model.layers.23.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
|
154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
|
157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
|
158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
|
159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
|
160 |
+
"model.layers.24.input_layernorm.weight": "model-00016-of-00018.safetensors",
|
161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
|
162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
|
163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
|
164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
|
165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
169 |
+
"model.layers.25.input_layernorm.weight": "model-00017-of-00018.safetensors",
|
170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
|
171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
|
174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
|
175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
|
176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
|
177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
|
178 |
+
"model.layers.26.input_layernorm.weight": "model-00018-of-00018.safetensors",
|
179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
|
180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
|
181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
|
182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
|
183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
|
184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
|
185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
|
186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
|
187 |
+
"model.layers.27.input_layernorm.weight": "model-00018-of-00018.safetensors",
|
188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
|
189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
|
190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
|
191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
|
192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
|
193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
|
194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
|
195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
|
196 |
+
"model.layers.3.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
|
199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
|
202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
|
203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
|
204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
|
205 |
+
"model.layers.4.input_layernorm.weight": "model-00004-of-00018.safetensors",
|
206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
|
207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
|
208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
|
209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
|
210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
214 |
+
"model.layers.5.input_layernorm.weight": "model-00005-of-00018.safetensors",
|
215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
|
216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
|
219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
|
220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
|
221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
|
222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
|
223 |
+
"model.layers.6.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
|
226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
|
227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
|
229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
|
230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
|
231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
|
232 |
+
"model.layers.7.input_layernorm.weight": "model-00006-of-00018.safetensors",
|
233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
|
234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
|
236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
|
237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
241 |
+
"model.layers.8.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
|
244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
|
247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
|
248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
|
249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
|
250 |
+
"model.layers.9.input_layernorm.weight": "model-00007-of-00018.safetensors",
|
251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
|
252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
|
253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
|
254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
|
255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
|
256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
|
257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
|
258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
|
259 |
+
"model.norm.weight": "model-00018-of-00018.safetensors"
|
260 |
+
}
|
261 |
+
}
|