Hugging Face's logo

YaxinLuo
/
Gamma-MoD-llava-hr-7b-stage1

PyTorch
llava
Model card Files Community
YaxinLuo commited on
Commit
28d07a6
•
1 Parent(s): 5b7480d

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +43 -0
  2. generation_config.json +9 -0
  3. pytorch_model-00001-of-00002.bin +3 -0
  4. pytorch_model-00002-of-00002.bin +3 -0
  5. pytorch_model.bin.index.json +0 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +35 -0
  9. trainer_state.json +31 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/vicuna/vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "delay_load": false,
8
+ "eos_token_id": 2,
9
+ "freeze_mm_mlp_adapter": false,
10
+ "freeze_vision": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "image_aspect_ratio": "pad",
14
+ "image_grid_pinpoints": null,
15
+ "initializer_range": 0.02,
16
+ "input_image_size": 1024,
17
+ "intermediate_size": 11008,
18
+ "is_multipath_encoder": true,
19
+ "max_position_embeddings": 4096,
20
+ "mm_hidden_size": 1024,
21
+ "mm_projector_type": "mlp2x_gelu",
22
+ "mm_use_im_patch_token": false,
23
+ "mm_use_im_start_end": false,
24
+ "mm_vision_select_feature": "patch",
25
+ "mm_vision_select_layer": -2,
26
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
27
+ "model_type": "llava",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 32,
30
+ "num_key_value_heads": 32,
31
+ "pad_token_id": 0,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.31.0",
38
+ "tune_mm_mlp_adapter": false,
39
+ "use_cache": true,
40
+ "use_mm_proj": true,
41
+ "vision_tower_slow": "convnext_large_mlp.clip_laion2b_ft_320",
42
+ "vocab_size": 32000
43
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.31.0"
9
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae9041e868397f6cdf44ce45f6f322196a9cecbb67a39d12bde69b2e03b6244
3
+ size 9976631973
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee30e77607219a0c182b535629e46ebd88215e03389d7637362a0b08b386aaa
3
+ size 4591604979
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2496,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.00019238168526356292,
5
+ "global_step": 1,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 2e-05,
13
+ "loss": 0.5618,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "step": 1,
19
+ "total_flos": 1508932845568.0,
20
+ "train_loss": 0.56182861328125,
21
+ "train_runtime": 31.3904,
22
+ "train_samples_per_second": 4.078,
23
+ "train_steps_per_second": 0.032
24
+ }
25
+ ],
26
+ "max_steps": 1,
27
+ "num_train_epochs": 1,
28
+ "total_flos": 1508932845568.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e8650b5672558890c54abe76b8d1d887d8fb334f4e853916f08e7c8fc0e049
3
+ size 6584