commit from linhh29@mail2.sysu.edu.cn
Browse files- added_tokens.json +4 -0
- config.json +45 -0
- configuration.json +1 -0
- generation_config.json +10 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +765 -0
- preprocessor_config.json +28 -0
- sft_args.json +239 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +60 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 32000,
|
3 |
+
"<pad>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/autodl-fs/llava-1.5-13b-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"hidden_size": 5120,
|
7 |
+
"ignore_index": -100,
|
8 |
+
"image_token_index": 32000,
|
9 |
+
"model_type": "llava",
|
10 |
+
"pad_token_id": 32001,
|
11 |
+
"projector_hidden_act": "gelu",
|
12 |
+
"text_config": {
|
13 |
+
"_name_or_path": "meta-llama/Llama-2-13b-hf",
|
14 |
+
"architectures": [
|
15 |
+
"LlamaForCausalLM"
|
16 |
+
],
|
17 |
+
"hidden_size": 5120,
|
18 |
+
"intermediate_size": 13824,
|
19 |
+
"max_position_embeddings": 4096,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 40,
|
22 |
+
"num_hidden_layers": 40,
|
23 |
+
"num_key_value_heads": 40,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"vocab_size": 32064
|
27 |
+
},
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.37.2",
|
31 |
+
"vision_config": {
|
32 |
+
"hidden_size": 1024,
|
33 |
+
"image_size": 336,
|
34 |
+
"intermediate_size": 4096,
|
35 |
+
"model_type": "clip_vision_model",
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_hidden_layers": 24,
|
38 |
+
"patch_size": 14,
|
39 |
+
"projection_dim": 768,
|
40 |
+
"vocab_size": 32000
|
41 |
+
},
|
42 |
+
"vision_feature_layer": -2,
|
43 |
+
"vision_feature_select_strategy": "default",
|
44 |
+
"vocab_size": 32064
|
45 |
+
}
|
configuration.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_sample": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"pad_token_id": 32001,
|
6 |
+
"temperature": 0.3,
|
7 |
+
"top_k": 20,
|
8 |
+
"top_p": 0.7,
|
9 |
+
"transformers_version": "4.41.0"
|
10 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87957bcdb949afc8e9d21efd2a060701f566b6f78abc5c68360455fd5c67de80
|
3 |
+
size 4962087464
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62885c5cfbc26153fef544a8bc09d2e28d65ad95865dcde0fdc6403aee849ef6
|
3 |
+
size 4970423272
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78a58b1b06caed4ad0f32539ab692f519ebb96a4661c7616255e529e5b68f222
|
3 |
+
size 4881273608
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55ef3cbc8db4855fcd12f9bc50405395bde4030ff62770611f7bbacb2437b648
|
3 |
+
size 4933723280
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2702bf68eb7f77fa9ec97f07a0f23b8e905a6475978d65aa9a83e1733625b4
|
3 |
+
size 4933723272
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c838cebe3ad425281d98cd627455d3f2acee1020667ce951243c0e9d9a453218
|
3 |
+
size 2021860536
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,765 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26702989312
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"language_model.lm_head.weight": "model-00006-of-00006.safetensors",
|
7 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
8 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
9 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
10 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
11 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
12 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
13 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
14 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
15 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
16 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
17 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
18 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
19 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
20 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
21 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
22 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
23 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
24 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
25 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
26 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
27 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
28 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
29 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
30 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
31 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
32 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
33 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
34 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
35 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
36 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
37 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
38 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
39 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
40 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
41 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
42 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
43 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
44 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
45 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
46 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
47 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
48 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
49 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
50 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
51 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
52 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
53 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
54 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
55 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
56 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
57 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
58 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
59 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
60 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
61 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
62 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
63 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
64 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
65 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
66 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
67 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
68 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
69 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
70 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
71 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
72 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
73 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
74 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
75 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
76 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
77 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
78 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
79 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
80 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
81 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
82 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
83 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
84 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
85 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
86 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
87 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
88 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
89 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
90 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
91 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
92 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
93 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
94 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
95 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
96 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
97 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
98 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
99 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
100 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
101 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
102 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
103 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
104 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
105 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
106 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
107 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
108 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
109 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
110 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
111 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
112 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
113 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
114 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
115 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
116 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
117 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
118 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
119 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
120 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
121 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
122 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
123 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
124 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
125 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
126 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
127 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
128 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
129 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
130 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
131 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
132 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
133 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
134 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
135 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
136 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
137 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
138 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
139 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
140 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
141 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
142 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
143 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
144 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
145 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
146 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
147 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
148 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
149 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
150 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
151 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
152 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
153 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
154 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
155 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
156 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
157 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
158 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
159 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
160 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
161 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
162 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
163 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
164 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
165 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
166 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
167 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
168 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
169 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
170 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
171 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
172 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
173 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
174 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
175 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
176 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
177 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
178 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
179 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
180 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
181 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
182 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
183 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
184 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
185 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
186 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
187 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
188 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
189 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
190 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
191 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
192 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
193 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
194 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
195 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
196 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
197 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
198 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
199 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
200 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
201 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
202 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
203 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
204 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
205 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
206 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
207 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
208 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
209 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
210 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
211 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
212 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
213 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
214 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
215 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
216 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
217 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
218 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
219 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
220 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
221 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
222 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
223 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
224 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
225 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
226 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
227 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
228 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
229 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
230 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
231 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
232 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
233 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
234 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
235 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
236 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
237 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
238 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
239 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
240 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
241 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
242 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
243 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
244 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
245 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
246 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
247 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
248 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
249 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
250 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
251 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
252 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
253 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
254 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
255 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
256 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
257 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
258 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
259 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
260 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
261 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
262 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
263 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
264 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
265 |
+
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
266 |
+
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
267 |
+
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
268 |
+
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
269 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
270 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
271 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
272 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
273 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
274 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
275 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
276 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
277 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
278 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
279 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
280 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
281 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
282 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
283 |
+
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
284 |
+
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
285 |
+
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
286 |
+
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
287 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
288 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
289 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
290 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
291 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
292 |
+
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
293 |
+
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
294 |
+
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
295 |
+
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
296 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
297 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
298 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
299 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
300 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
301 |
+
"language_model.model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
302 |
+
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
303 |
+
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
304 |
+
"language_model.model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
305 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
306 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
307 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
308 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
309 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
310 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
311 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
312 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
313 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
314 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
315 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
316 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
317 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
318 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
319 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
320 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
321 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
322 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
323 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
324 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
325 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
326 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
327 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
328 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
329 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
330 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
331 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
332 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
333 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
334 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
335 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
336 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
337 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
338 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
339 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
340 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
341 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
342 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
343 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
344 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
345 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
346 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
347 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
348 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
349 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
350 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
351 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
352 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
353 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
354 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
355 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
356 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
357 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
358 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
359 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
360 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
361 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
362 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
363 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
364 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
365 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
366 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
367 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
368 |
+
"language_model.model.norm.weight": "model-00006-of-00006.safetensors",
|
369 |
+
"multi_modal_projector.linear_1.bias": "model-00001-of-00006.safetensors",
|
370 |
+
"multi_modal_projector.linear_1.weight": "model-00001-of-00006.safetensors",
|
371 |
+
"multi_modal_projector.linear_2.bias": "model-00001-of-00006.safetensors",
|
372 |
+
"multi_modal_projector.linear_2.weight": "model-00001-of-00006.safetensors",
|
373 |
+
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00006.safetensors",
|
374 |
+
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00006.safetensors",
|
375 |
+
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00006.safetensors",
|
376 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
377 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
378 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
379 |
+
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
380 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
381 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
382 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
383 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
384 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
385 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
386 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
387 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
388 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
389 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
390 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
391 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
392 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
393 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
394 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
395 |
+
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
396 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
397 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
398 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
399 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
400 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
401 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
402 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
403 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
404 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
405 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
406 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
407 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
408 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
409 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
410 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
411 |
+
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
412 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
413 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
414 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
415 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
416 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
417 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
418 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
419 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
420 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
421 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
422 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
423 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
424 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
425 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
426 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
427 |
+
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
428 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
429 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
430 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
431 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
432 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
433 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
434 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
435 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
436 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
437 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
438 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
439 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
440 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
441 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
442 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
443 |
+
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
444 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
445 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
446 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
447 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
448 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
449 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
450 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
451 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
452 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
453 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
454 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
455 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
456 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
457 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
458 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
459 |
+
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
460 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
461 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
462 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
463 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
464 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
465 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
466 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
467 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
468 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
469 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
470 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
471 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
472 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
473 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
474 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
475 |
+
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
476 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
477 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
478 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
479 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
480 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
481 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
482 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
483 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
484 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
485 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
486 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
487 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
488 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
489 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
490 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
491 |
+
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
492 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
493 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
494 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
495 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
496 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
497 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
498 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
499 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
500 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
501 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
502 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
503 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
504 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
505 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
506 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
507 |
+
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
508 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
509 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
510 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
511 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
512 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
513 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
514 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
515 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
516 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
517 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
518 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
519 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
520 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
521 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
522 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
523 |
+
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
524 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
525 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
526 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
527 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
528 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
529 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
530 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
531 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
532 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
533 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
534 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
535 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
536 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
537 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
538 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
539 |
+
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
540 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
541 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
542 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
543 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
544 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
545 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
546 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
547 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
548 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
549 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
550 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
551 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
552 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
553 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
554 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
555 |
+
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
556 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
557 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
558 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
559 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
560 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
561 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
562 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
563 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
564 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
565 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
566 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
567 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
568 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
569 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
570 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
571 |
+
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
572 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
573 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
574 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
575 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
576 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
577 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
578 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
579 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
580 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
581 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
582 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
583 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
584 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
585 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
586 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
587 |
+
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
588 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
589 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
590 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
591 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
592 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
593 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
594 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
595 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
596 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
597 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
598 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
599 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
600 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
601 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
602 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
603 |
+
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
604 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
605 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
606 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
607 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
608 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
609 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
610 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
611 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
612 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
613 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
614 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
615 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
616 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
617 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
618 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
619 |
+
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
620 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
621 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
622 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
623 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
624 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
625 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
626 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
627 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
628 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
629 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
630 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
631 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
632 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
633 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
634 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
635 |
+
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
636 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
637 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
638 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
639 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
640 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
641 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
642 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
643 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
644 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
645 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
646 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
647 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
648 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
649 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
650 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
651 |
+
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
652 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
653 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
654 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
655 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
656 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
657 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
658 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
659 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
660 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
661 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
662 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
663 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
664 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
665 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
666 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
667 |
+
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
668 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
669 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
670 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
671 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
672 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
673 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
674 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
675 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
676 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
677 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
678 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
679 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
680 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
681 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
682 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
683 |
+
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
684 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
685 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
686 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
687 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
688 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
689 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
690 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
691 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
692 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
693 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
694 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
695 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
696 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
697 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
698 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
699 |
+
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
700 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
701 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
702 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
703 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
704 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
705 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
706 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
707 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
708 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
709 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
710 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
711 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
712 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
713 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
714 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
715 |
+
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
716 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
717 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
718 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
719 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
720 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
721 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
722 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
723 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
724 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
725 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
726 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
727 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
728 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
729 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
730 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
731 |
+
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
732 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
733 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
734 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
735 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
736 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
737 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
738 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
739 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
740 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
741 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
742 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
743 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
744 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00006.safetensors",
|
745 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00006.safetensors",
|
746 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00006.safetensors",
|
747 |
+
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00006.safetensors",
|
748 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00006.safetensors",
|
749 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00006.safetensors",
|
750 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00006.safetensors",
|
751 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00006.safetensors",
|
752 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
753 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
754 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00006.safetensors",
|
755 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
756 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
757 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
758 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
759 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
760 |
+
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00006.safetensors",
|
761 |
+
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00006.safetensors",
|
762 |
+
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00006.safetensors",
|
763 |
+
"vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00006.safetensors"
|
764 |
+
}
|
765 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 336,
|
4 |
+
"width": 336
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.48145466,
|
13 |
+
0.4578275,
|
14 |
+
0.40821073
|
15 |
+
],
|
16 |
+
"image_processor_type": "CLIPImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"processor_class": "LlavaProcessor",
|
23 |
+
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 336
|
27 |
+
}
|
28 |
+
}
|
sft_args.json
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "llava1_5-13b-instruct",
|
3 |
+
"model_id_or_path": "/root/autodl-fs/llava-1.5-13b-hf",
|
4 |
+
"model_revision": "master",
|
5 |
+
"sft_type": "full",
|
6 |
+
"freeze_parameters": 0.0,
|
7 |
+
"additional_trainable_parameters": [],
|
8 |
+
"tuner_backend": "peft",
|
9 |
+
"template_type": "llava1_5",
|
10 |
+
"output_dir": "/root/autodl-tmp/SC_data/output/llava1_5-13b-instruct/v2-20240806-153549",
|
11 |
+
"add_output_dir_suffix": true,
|
12 |
+
"ddp_backend": null,
|
13 |
+
"ddp_find_unused_parameters": null,
|
14 |
+
"ddp_broadcast_buffers": null,
|
15 |
+
"seed": 42,
|
16 |
+
"resume_from_checkpoint": null,
|
17 |
+
"resume_only_model": false,
|
18 |
+
"ignore_data_skip": false,
|
19 |
+
"dtype": "bf16",
|
20 |
+
"packing": false,
|
21 |
+
"train_backend": "transformers",
|
22 |
+
"tp": 1,
|
23 |
+
"pp": 1,
|
24 |
+
"min_lr": null,
|
25 |
+
"sequence_parallel": false,
|
26 |
+
"dataset": [
|
27 |
+
"/root/autodl-tmp/SC_data/DPO_13b.json"
|
28 |
+
],
|
29 |
+
"val_dataset": [],
|
30 |
+
"dataset_seed": 42,
|
31 |
+
"dataset_test_ratio": 0.01,
|
32 |
+
"use_loss_scale": false,
|
33 |
+
"loss_scale_config_path": "/root/autodl-tmp/swift/swift/llm/agent/default_loss_scale_config.json",
|
34 |
+
"system": null,
|
35 |
+
"tools_prompt": "react_en",
|
36 |
+
"max_length": 2048,
|
37 |
+
"truncation_strategy": "delete",
|
38 |
+
"check_dataset_strategy": "none",
|
39 |
+
"model_name": [
|
40 |
+
null,
|
41 |
+
null
|
42 |
+
],
|
43 |
+
"model_author": [
|
44 |
+
null,
|
45 |
+
null
|
46 |
+
],
|
47 |
+
"quant_method": null,
|
48 |
+
"quantization_bit": 0,
|
49 |
+
"hqq_axis": 0,
|
50 |
+
"hqq_dynamic_config_path": null,
|
51 |
+
"bnb_4bit_comp_dtype": "bf16",
|
52 |
+
"bnb_4bit_quant_type": "nf4",
|
53 |
+
"bnb_4bit_use_double_quant": true,
|
54 |
+
"bnb_4bit_quant_storage": null,
|
55 |
+
"rescale_image": -1,
|
56 |
+
"target_modules": "^(language_model|multi_modal_projector)(?!.*(lm_head|output|emb|wte|shared)).*",
|
57 |
+
"target_regex": null,
|
58 |
+
"modules_to_save": [],
|
59 |
+
"lora_rank": 8,
|
60 |
+
"lora_alpha": 32,
|
61 |
+
"lora_dropout": 0.05,
|
62 |
+
"lora_bias_trainable": "none",
|
63 |
+
"lora_dtype": null,
|
64 |
+
"lora_lr_ratio": null,
|
65 |
+
"use_rslora": false,
|
66 |
+
"use_dora": false,
|
67 |
+
"init_lora_weights": true,
|
68 |
+
"fourier_n_frequency": 2000,
|
69 |
+
"fourier_scaling": 300.0,
|
70 |
+
"rope_scaling": null,
|
71 |
+
"boft_block_size": 4,
|
72 |
+
"boft_block_num": 0,
|
73 |
+
"boft_n_butterfly_factor": 1,
|
74 |
+
"boft_dropout": 0.0,
|
75 |
+
"vera_rank": 256,
|
76 |
+
"vera_projection_prng_key": 0,
|
77 |
+
"vera_dropout": 0.0,
|
78 |
+
"vera_d_initial": 0.1,
|
79 |
+
"adapter_act": "gelu",
|
80 |
+
"adapter_length": 128,
|
81 |
+
"use_galore": false,
|
82 |
+
"galore_target_modules": null,
|
83 |
+
"galore_rank": 128,
|
84 |
+
"galore_update_proj_gap": 50,
|
85 |
+
"galore_scale": 1.0,
|
86 |
+
"galore_proj_type": "std",
|
87 |
+
"galore_optim_per_parameter": false,
|
88 |
+
"galore_with_embedding": false,
|
89 |
+
"galore_quantization": false,
|
90 |
+
"galore_proj_quant": false,
|
91 |
+
"galore_proj_bits": 4,
|
92 |
+
"galore_proj_group_size": 256,
|
93 |
+
"galore_cos_threshold": 0.4,
|
94 |
+
"galore_gamma_proj": 2,
|
95 |
+
"galore_queue_size": 5,
|
96 |
+
"adalora_target_r": 8,
|
97 |
+
"adalora_init_r": 12,
|
98 |
+
"adalora_tinit": 0,
|
99 |
+
"adalora_tfinal": 0,
|
100 |
+
"adalora_deltaT": 1,
|
101 |
+
"adalora_beta1": 0.85,
|
102 |
+
"adalora_beta2": 0.85,
|
103 |
+
"adalora_orth_reg_weight": 0.5,
|
104 |
+
"ia3_feedforward_modules": [],
|
105 |
+
"llamapro_num_new_blocks": 4,
|
106 |
+
"llamapro_num_groups": null,
|
107 |
+
"neftune_noise_alpha": null,
|
108 |
+
"neftune_backend": "transformers",
|
109 |
+
"lisa_activated_layers": 0,
|
110 |
+
"lisa_step_interval": 20,
|
111 |
+
"gradient_checkpointing": true,
|
112 |
+
"deepspeed": null,
|
113 |
+
"batch_size": 1,
|
114 |
+
"eval_batch_size": 1,
|
115 |
+
"num_train_epochs": 8,
|
116 |
+
"max_steps": -1,
|
117 |
+
"optim": "adamw_torch",
|
118 |
+
"adam_beta1": 0.9,
|
119 |
+
"adam_beta2": 0.95,
|
120 |
+
"adam_epsilon": 1e-08,
|
121 |
+
"learning_rate": 5e-05,
|
122 |
+
"weight_decay": 0.1,
|
123 |
+
"gradient_accumulation_steps": 16,
|
124 |
+
"max_grad_norm": 1,
|
125 |
+
"predict_with_generate": false,
|
126 |
+
"lr_scheduler_type": "cosine",
|
127 |
+
"lr_scheduler_kwargs": {},
|
128 |
+
"warmup_ratio": 0.03,
|
129 |
+
"warmup_steps": 0,
|
130 |
+
"eval_steps": 50,
|
131 |
+
"save_steps": 50,
|
132 |
+
"save_only_model": false,
|
133 |
+
"save_total_limit": 2,
|
134 |
+
"logging_steps": 5,
|
135 |
+
"acc_steps": 1,
|
136 |
+
"dataloader_num_workers": 1,
|
137 |
+
"dataloader_pin_memory": true,
|
138 |
+
"dataloader_drop_last": false,
|
139 |
+
"push_to_hub": false,
|
140 |
+
"hub_model_id": null,
|
141 |
+
"hub_token": null,
|
142 |
+
"hub_private_repo": false,
|
143 |
+
"push_hub_strategy": "push_best",
|
144 |
+
"test_oom_error": false,
|
145 |
+
"disable_tqdm": false,
|
146 |
+
"lazy_tokenize": true,
|
147 |
+
"preprocess_num_proc": 1,
|
148 |
+
"use_flash_attn": null,
|
149 |
+
"ignore_args_error": false,
|
150 |
+
"check_model_is_latest": true,
|
151 |
+
"logging_dir": "/root/autodl-tmp/SC_data/output/llava1_5-13b-instruct/v2-20240806-153549/runs",
|
152 |
+
"report_to": [
|
153 |
+
"tensorboard"
|
154 |
+
],
|
155 |
+
"acc_strategy": "token",
|
156 |
+
"save_on_each_node": false,
|
157 |
+
"evaluation_strategy": "steps",
|
158 |
+
"save_strategy": "steps",
|
159 |
+
"save_safetensors": true,
|
160 |
+
"gpu_memory_fraction": null,
|
161 |
+
"include_num_input_tokens_seen": false,
|
162 |
+
"local_repo_path": null,
|
163 |
+
"custom_register_path": null,
|
164 |
+
"custom_dataset_info": null,
|
165 |
+
"device_map_config_path": null,
|
166 |
+
"device_max_memory": [],
|
167 |
+
"max_new_tokens": 2048,
|
168 |
+
"do_sample": true,
|
169 |
+
"temperature": 0.3,
|
170 |
+
"top_k": 20,
|
171 |
+
"top_p": 0.7,
|
172 |
+
"repetition_penalty": 1.0,
|
173 |
+
"num_beams": 1,
|
174 |
+
"fsdp": "",
|
175 |
+
"fsdp_config": null,
|
176 |
+
"sequence_parallel_size": 1,
|
177 |
+
"model_layer_cls_name": null,
|
178 |
+
"metric_warmup_step": 0,
|
179 |
+
"fsdp_num": 1,
|
180 |
+
"per_device_train_batch_size": null,
|
181 |
+
"per_device_eval_batch_size": null,
|
182 |
+
"eval_strategy": null,
|
183 |
+
"self_cognition_sample": 0,
|
184 |
+
"train_dataset_mix_ratio": 0.0,
|
185 |
+
"train_dataset_mix_ds": [
|
186 |
+
"ms-bench"
|
187 |
+
],
|
188 |
+
"train_dataset_sample": -1,
|
189 |
+
"val_dataset_sample": null,
|
190 |
+
"safe_serialization": null,
|
191 |
+
"only_save_model": null,
|
192 |
+
"neftune_alpha": null,
|
193 |
+
"deepspeed_config_path": null,
|
194 |
+
"model_cache_dir": null,
|
195 |
+
"lora_dropout_p": null,
|
196 |
+
"lora_target_modules": [],
|
197 |
+
"lora_target_regex": null,
|
198 |
+
"lora_modules_to_save": [],
|
199 |
+
"boft_target_modules": [],
|
200 |
+
"boft_modules_to_save": [],
|
201 |
+
"vera_target_modules": [],
|
202 |
+
"vera_modules_to_save": [],
|
203 |
+
"ia3_target_modules": [],
|
204 |
+
"ia3_modules_to_save": [],
|
205 |
+
"custom_train_dataset_path": [],
|
206 |
+
"custom_val_dataset_path": [],
|
207 |
+
"rlhf_type": "dpo",
|
208 |
+
"ref_model_type": null,
|
209 |
+
"ref_model_id_or_path": null,
|
210 |
+
"ref_model_free": false,
|
211 |
+
"max_prompt_length": 1024,
|
212 |
+
"beta": 0.1,
|
213 |
+
"label_smoothing": 0.0,
|
214 |
+
"loss_type": "sigmoid",
|
215 |
+
"sft_beta": 0.1,
|
216 |
+
"simpo_gamma": 1.0,
|
217 |
+
"cpo_alpha": 1.0,
|
218 |
+
"desirable_weight": 1.0,
|
219 |
+
"undesirable_weight": 1.0,
|
220 |
+
"use_self_cognition": false,
|
221 |
+
"is_multimodal": true,
|
222 |
+
"is_vision": true,
|
223 |
+
"lora_use_embedding": false,
|
224 |
+
"lora_use_all": false,
|
225 |
+
"lora_m2s_use_embedding": false,
|
226 |
+
"lora_m2s_use_ln": false,
|
227 |
+
"torch_dtype": "torch.bfloat16",
|
228 |
+
"fp16": false,
|
229 |
+
"bf16": true,
|
230 |
+
"rank": -1,
|
231 |
+
"local_rank": -1,
|
232 |
+
"world_size": 1,
|
233 |
+
"local_world_size": 1,
|
234 |
+
"bnb_4bit_compute_dtype": "torch.bfloat16",
|
235 |
+
"load_in_4bit": false,
|
236 |
+
"load_in_8bit": false,
|
237 |
+
"train_sampler_random": true,
|
238 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/root/autodl-tmp/SC_data/output/llava1_5-13b-instruct/v2-20240806-153549', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=5e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=8, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/autodl-tmp/SC_data/output/llava1_5-13b-instruct/v2-20240806-153549/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/autodl-tmp/SC_data/output/llava1_5-13b-instruct/v2-20240806-153549', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"do_sample\": true,\n \"eos_token_id\": 2,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 32001,\n \"temperature\": 0.3,\n \"top_k\": 20,\n \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
|
239 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"pad_token": {
|
11 |
+
"content": "<pad>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<pad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"clean_up_tokenization_spaces": false,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"legacy": false,
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"padding_side": "left",
|
54 |
+
"processor_class": "LlavaProcessor",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"tokenizer_class": "LlamaTokenizer",
|
57 |
+
"trust_remote_code": false,
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false
|
60 |
+
}
|