Hugging Face's logo

tianhux2
/
lc1

Safetensors
Model card Files
xet
 Community
tianhux2 commited on
Commit
45803d5
·
verified ·
1 Parent(s): 9930b7e

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1000/config.json +65 -0
  2. checkpoint-1000/generation_config.json +10 -0
  3. checkpoint-1000/model.safetensors +3 -0
  4. checkpoint-1000/processor_config.json +35 -0
  5. checkpoint-1000/tokenizer.json +0 -0
  6. checkpoint-1000/tokenizer_config.json +0 -0
  7. checkpoint-1200/config.json +65 -0
  8. checkpoint-1200/generation_config.json +10 -0
  9. checkpoint-1200/model.safetensors +3 -0
  10. checkpoint-1200/processor_config.json +35 -0
  11. checkpoint-1200/tokenizer.json +0 -0
  12. checkpoint-1200/tokenizer_config.json +0 -0
  13. checkpoint-1400/config.json +65 -0
  14. checkpoint-1400/generation_config.json +10 -0
  15. checkpoint-1400/model.safetensors +3 -0
  16. checkpoint-1400/processor_config.json +35 -0
  17. checkpoint-1400/tokenizer.json +0 -0
  18. checkpoint-1400/tokenizer_config.json +0 -0
  19. checkpoint-1600/config.json +65 -0
  20. checkpoint-1600/generation_config.json +10 -0
  21. checkpoint-1600/model.safetensors +3 -0
  22. checkpoint-1600/processor_config.json +35 -0
  23. checkpoint-1600/tokenizer.json +0 -0
  24. checkpoint-1600/tokenizer_config.json +0 -0
  25. checkpoint-1800/config.json +65 -0
  26. checkpoint-1800/generation_config.json +10 -0
  27. checkpoint-1800/model.safetensors +3 -0
  28. checkpoint-1800/processor_config.json +35 -0
  29. checkpoint-1800/tokenizer.json +0 -0
  30. checkpoint-1800/tokenizer_config.json +0 -0
  31. checkpoint-200/config.json +65 -0
  32. checkpoint-200/generation_config.json +10 -0
  33. checkpoint-200/model.safetensors +3 -0
  34. checkpoint-200/processor_config.json +35 -0
  35. checkpoint-200/tokenizer.json +0 -0
  36. checkpoint-200/tokenizer_config.json +0 -0
  37. checkpoint-2000/config.json +65 -0
  38. checkpoint-2000/generation_config.json +10 -0
  39. checkpoint-2000/model.safetensors +3 -0
  40. checkpoint-2000/processor_config.json +35 -0
  41. checkpoint-2000/tokenizer.json +0 -0
  42. checkpoint-2000/tokenizer_config.json +0 -0
  43. checkpoint-2200/config.json +65 -0
  44. checkpoint-2200/generation_config.json +10 -0
  45. checkpoint-2200/model.safetensors +3 -0
  46. checkpoint-2200/processor_config.json +35 -0
  47. checkpoint-2200/tokenizer.json +0 -0
  48. checkpoint-2200/tokenizer_config.json +0 -0
  49. checkpoint-2400/config.json +65 -0
  50. checkpoint-2400/generation_config.json +10 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf2ea3f9d74449ed9828e68674d2c8ad0156943600ec23cf739814ff0697e1e
3
+ size 26703091920
checkpoint-1000/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-1200/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-1200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e87793894e7a559a350197ad5c096eb816196d4d57a4beebc7117201b5442b1
3
+ size 26703091920
checkpoint-1200/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-1200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-1400/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d85dae4f7b6f6a0217e64f38e4cec991265ad8865ac9f7605ee795075733bb
3
+ size 26703091920
checkpoint-1400/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-1400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-1600/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-1600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e9b21d046d59aa0dd255700007ebddaeba8df9bf0b4c57bbd4f8573629d445
3
+ size 26703091920
checkpoint-1600/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-1600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1600/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1800/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-1800/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-1800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5184f4e4025c3ec821491ff625de1c7a06ce07365c164ad63946fc199c3cf2ec
3
+ size 26703091920
checkpoint-1800/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-1800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1800/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06775cb6b58acab7da040f4843f412de08c9a9399fa1f0e952e60015d194f2ef
3
+ size 26703091920
checkpoint-200/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9390ec1e8faa64f8ce0521a67ba202d494b51887fb51a7c2ef97d42c91d2a534
3
+ size 26703091920
checkpoint-2000/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2200/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-2200/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }
checkpoint-2200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4223fd1193f3e20e6a93dc60ad1a8bd6b93448ad4f0818f96b7c6c36f7783b0d
3
+ size 26703091920
checkpoint-2200/processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": true,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "CLIPImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "shortest_edge": 336
28
+ }
29
+ },
30
+ "image_token": "<image>",
31
+ "num_additional_image_tokens": 0,
32
+ "patch_size": null,
33
+ "processor_class": "LlavaProcessor",
34
+ "vision_feature_select_strategy": null
35
+ }
checkpoint-2200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2200/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2400/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_seq_length": 576,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "pad_token_id": 32001,
11
+ "projector_hidden_act": "gelu",
12
+ "text_config": {
13
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
14
+ "architectures": [
15
+ "LlamaForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "bos_token_id": 1,
20
+ "dtype": "float16",
21
+ "eos_token_id": 2,
22
+ "head_dim": 128,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 5120,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 13824,
27
+ "max_position_embeddings": 4096,
28
+ "mlp_bias": false,
29
+ "model_type": "llama",
30
+ "num_attention_heads": 40,
31
+ "num_hidden_layers": 40,
32
+ "num_key_value_heads": 40,
33
+ "pad_token_id": 0,
34
+ "pretraining_tp": 1,
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_parameters": {
37
+ "rope_theta": 10000.0,
38
+ "rope_type": "default"
39
+ },
40
+ "tie_word_embeddings": false,
41
+ "use_cache": true,
42
+ "vocab_size": 32064
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.1.0",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "quick_gelu",
49
+ "hidden_size": 1024,
50
+ "image_size": 336,
51
+ "initializer_factor": 1.0,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "layer_norm_eps": 1e-05,
55
+ "model_type": "clip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 24,
59
+ "patch_size": 14,
60
+ "projection_dim": 768,
61
+ "vocab_size": 32000
62
+ },
63
+ "vision_feature_layer": -2,
64
+ "vision_feature_select_strategy": "default"
65
+ }
checkpoint-2400/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 32001,
8
+ "transformers_version": "5.1.0",
9
+ "use_cache": true
10
+ }