Hugging Face's logo

YanweiLi
/
MGM-34B

Text Generation
Transformers
Safetensors
vision-language model
llama
yi
generation
conversational
Inference Endpoints
Model card Files Community
YanweiLi commited on
Commit
ac4c1ad
•
1 Parent(s): 269797e

First model version

Browse files
Files changed (23) hide show
  1. config.json +56 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00015.safetensors +3 -0
  4. model-00002-of-00015.safetensors +3 -0
  5. model-00003-of-00015.safetensors +3 -0
  6. model-00004-of-00015.safetensors +3 -0
  7. model-00005-of-00015.safetensors +3 -0
  8. model-00006-of-00015.safetensors +3 -0
  9. model-00007-of-00015.safetensors +3 -0
  10. model-00008-of-00015.safetensors +3 -0
  11. model-00009-of-00015.safetensors +3 -0
  12. model-00010-of-00015.safetensors +3 -0
  13. model-00011-of-00015.safetensors +3 -0
  14. model-00012-of-00015.safetensors +3 -0
  15. model-00013-of-00015.safetensors +3 -0
  16. model-00014-of-00015.safetensors +3 -0
  17. model-00015-of-00015.safetensors +3 -0
  18. model.safetensors.index.json +0 -0
  19. special_tokens_map.json +24 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +61 -0
  22. trainer_state.json +0 -0
  23. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "model_zoo/LLM/Nous-Hermes-2-Yi-34B",
3
+ "architectures": [
4
+ "LlavaLlamaUniForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "aux_img_fold": false,
9
+ "aux_with_fpn": false,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 7,
12
+ "freeze_mm_mlp_adapter": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 7168,
15
+ "image_aspect_ratio": "pad",
16
+ "image_global": false,
17
+ "image_grid": 1,
18
+ "image_grid_pinpoints": null,
19
+ "image_size_aux": 768,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 20480,
22
+ "max_position_embeddings": 4096,
23
+ "mm_hidden_size": 1024,
24
+ "mm_hidden_size_aux": 2880,
25
+ "mm_projector_lr": null,
26
+ "mm_projector_type": "mlp2x_gelu",
27
+ "mm_use_im_patch_token": false,
28
+ "mm_use_im_start_end": false,
29
+ "mm_vision_select_feature": "patch",
30
+ "mm_vision_select_layer": -2,
31
+ "mm_vision_tower": "model_zoo/OpenAI/clip-vit-large-patch14-336",
32
+ "mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
33
+ "model_type": "llava_uni",
34
+ "num_attention_heads": 56,
35
+ "num_hidden_layers": 60,
36
+ "num_key_value_heads": 8,
37
+ "optimize_vision_tower": false,
38
+ "optimize_vision_tower_aux": false,
39
+ "pad_token_id": 0,
40
+ "pretraining_tp": 1,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": null,
43
+ "rope_theta": 5000000.0,
44
+ "tie_word_embeddings": false,
45
+ "tokenizer_model_max_length": 2048,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.36.2",
49
+ "tune_mm_mlp_adapter": false,
50
+ "unified_resampler": "simple_sum",
51
+ "use_cache": true,
52
+ "use_mm_proj": true,
53
+ "use_same_im_pos": false,
54
+ "video_grid": -1,
55
+ "vocab_size": 64000
56
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
+ }
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0ea70b8df3e22f8970d75bfb446191589f0579c86ea1026b768a9e4fa122cf
3
+ size 4793130760
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b205bb1a396d12b46b06fe114f09535556fa984897ec76bdc41bddf1934495c0
3
+ size 4756459720
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7548e57da39c32974dd37ac9f23591f42b9cc328ef2d098a7ad353f1514a5c
3
+ size 4991370136
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b0723fdbb667d8fa8a8833400cafa37bf9984fab3455856d8e2d261b7e4985
3
+ size 4756459760
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed36a036dce7e20d4a73ecd51c38a9ce18d293d6f41ed99d1c9db99dece1f80
3
+ size 4756459760
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d39ef6b2b7a5aaaae12a004cca953f6444293baebd41c15c63b53c222465c8d
3
+ size 4991370160
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa75a959cd210fc25a515ca0f44d2319dff0378db22b6d07d5ed09a468bf06d
3
+ size 4756459760
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe3c91dfcc53858ad5a1863b82e7f5b0e6602acb141355d3519373abe198c09
3
+ size 4756459760
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b155f1d44ea24b818388a4492cee9797562e18505fd04e8ce269bb29babc20f
3
+ size 4991370160
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcc6396cad13084306da8cd9cd95834727198990cc23c2bc1875715b5c00b98
3
+ size 4756459760
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3237a0cfcae4c83af9007fb66e8f5ac7c069e586f5d02eac88befc0b1a1db6a4
3
+ size 4756459760
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5b69dabdfe61185eaf3ebc2a77fd1cd9c86c0cc83e82b612af5f93343e2500
3
+ size 4991370160
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbbdb41ce8c7247a542dbf4a18c79f22de876773514db47b59713e27ff7414e
3
+ size 4756459760
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0fdf06a3890140d99bbc665d52fac575c93bd87fee84cd7e428c722e3653d1
3
+ size 4756459760
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80180ac5a595f18181e42d3c45e2a70b79b8228029b0bfc6820d8ae0fe2213ba
3
+ size 2342123256
model.safetensors.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": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "6": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "7": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<|startoftext|>",
47
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
48
+ "clean_up_tokenization_spaces": false,
49
+ "eos_token": "<|im_end|>",
50
+ "legacy": true,
51
+ "model_max_length": 2048,
52
+ "pad_token": "<unk>",
53
+ "padding_side": "right",
54
+ "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
+ "tokenizer_class": "LlamaTokenizer",
57
+ "trust_remote_code": false,
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": false,
60
+ "use_fast": true
61
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f810b9e3822acd3cd84fec4518027e8523f27e0ad16d88dc8bc93db6a2c3489
3
+ size 6459