Hugging Face's logo

dvtoan18
/
Minigemini-34b-200-steps

Text Generation
Transformers
Safetensors
mini_gemini
conversational
Inference Endpoints
Model card Files Community
dvtoan18 commited on
Commit
0f28195
•
1 Parent(s): bc7a260

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. config.json +54 -0
  2. generation_config.json +7 -0
  3. latest +1 -0
  4. model-00001-of-00015.safetensors +3 -0
  5. model-00002-of-00015.safetensors +3 -0
  6. model-00003-of-00015.safetensors +3 -0
  7. model-00004-of-00015.safetensors +3 -0
  8. model-00005-of-00015.safetensors +3 -0
  9. model-00006-of-00015.safetensors +3 -0
  10. model-00007-of-00015.safetensors +3 -0
  11. model-00008-of-00015.safetensors +3 -0
  12. model-00009-of-00015.safetensors +3 -0
  13. model-00010-of-00015.safetensors +3 -0
  14. model-00011-of-00015.safetensors +3 -0
  15. model-00012-of-00015.safetensors +3 -0
  16. model-00013-of-00015.safetensors +3 -0
  17. model-00014-of-00015.safetensors +3 -0
  18. model-00015-of-00015.safetensors +3 -0
  19. model.safetensors.index.json +0 -0
  20. special_tokens_map.json +24 -0
  21. tokenizer.model +3 -0
  22. tokenizer_config.json +61 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Mini-Gemini-34B-HD",
3
+ "architectures": [
4
+ "MiniGeminiLlamaForCausalLM"
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": true,
17
+ "image_grid": 2,
18
+ "image_grid_pinpoints": null,
19
+ "image_size_aux": 1536,
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": "mini_gemini",
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": 4096,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.36.2",
49
+ "tune_mm_mlp_adapter": false,
50
+ "use_cache": false,
51
+ "use_mm_proj": true,
52
+ "video_grid": -1,
53
+ "vocab_size": 64000
54
+ }
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
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step200
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f9133fcb82dd6a45dae45ae611aac35ba913a640aaeec2419649bfce6b044d4
3
+ size 4793130760
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4b98ee24649446eae79e7345bcd1319fe039d6efbff76f1e2dd483875b190b
3
+ size 4756459720
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ea80093723e59fa47d8b05f3a38e501173845b5892b1e0f17554dcd7e75f3d
3
+ size 4991370136
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe57a94f6d9572c1d166645e1c97b4b1014fd8c798d5027da6b9028cfcc866d
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:ee9f4eebf2243c1553f45f1a263385038f9614953d457e3e2be829bc7ab9fdb5
3
+ size 4756459760
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d79ddc192581e55118d684dc516cfcb22e1465fbc9ecb61197a1be6b6b21285
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:b5038f88392c45f59e44a04993fc97b7e8e449a09842afdfedb6208f0be630d5
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:c743efdc60d8772f2d9904a42e616b5045d70b6dfdcf18ada2a584bcc88e7d4c
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:e9a0379abe17836ecfe630571b14dc4b4cbc631c5aa21f629ce39af7fac7bed0
3
+ size 4991370160
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c9c054f39877f39e8b928f7b7ff92f9cdd152512aa8ea293c3ca4c6ee15813
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:a13a856b4db0e861e635b96b32718500f0e7fde661948f8bb49b9e325fb115de
3
+ size 4756459760
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea4b91e582dab32924eec27d5546e9b94a4b1924b169887bb273a8a6e536d83
3
+ size 4991370160
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdf32ceb5f6af6ea922036ed48daa5248e9dd986b3b6f0e520a0b8fde858dfe
3
+ size 4756459760
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec12d92d234480b6e34b159aa2f40dc7faee865edf238a6fbd7a822c1162b1a
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:c6768037f481451e68577ee8d4b83988ca2aaefd333c1df24f10d7746f34554f
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": 4096,
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
+ }