Hugging Face's logo

Thanmay
/
gemma_exps

Model card Files
xet
Community
Thanmay commited on
Commit
f6667e0
·
1 Parent(s): 5a6e519

Initial commit with LFS tracked files

Browse files
Files changed (49) hide show
  1. gemma_3_1B_LR_1e-3/added_tokens.json +3 -3
  2. gemma_3_1B_LR_1e-3/config.json +3 -34
  3. gemma_3_1B_LR_1e-3/generation_config.json +3 -13
  4. gemma_3_1B_LR_1e-3/special_tokens_map.json +3 -33
  5. gemma_3_1B_LR_1e-3/tokenizer_config.json +0 -0
  6. gemma_3_1B_LR_1e-4/added_tokens.json +3 -3
  7. gemma_3_1B_LR_1e-4/config.json +3 -34
  8. gemma_3_1B_LR_1e-4/generation_config.json +3 -13
  9. gemma_3_1B_LR_1e-4/special_tokens_map.json +3 -33
  10. gemma_3_1B_LR_1e-4/tokenizer.json +3 -0
  11. gemma_3_1B_LR_1e-4/tokenizer_config.json +0 -0
  12. gemma_3_1B_LR_1e-5/added_tokens.json +3 -3
  13. gemma_3_1B_LR_1e-5/config.json +3 -34
  14. gemma_3_1B_LR_1e-5/generation_config.json +3 -13
  15. gemma_3_1B_LR_1e-5/special_tokens_map.json +3 -33
  16. gemma_3_1B_LR_1e-5/tokenizer.json +3 -0
  17. gemma_3_1B_LR_1e-5/tokenizer_config.json +0 -0
  18. gemma_3_1B_LR_5e-3/added_tokens.json +3 -3
  19. gemma_3_1B_LR_5e-3/config.json +3 -34
  20. gemma_3_1B_LR_5e-3/generation_config.json +3 -13
  21. gemma_3_1B_LR_5e-3/special_tokens_map.json +3 -33
  22. gemma_3_1B_LR_5e-3/tokenizer.json +3 -0
  23. gemma_3_1B_LR_5e-3/tokenizer_config.json +0 -0
  24. gemma_3_1B_LR_5e-4/added_tokens.json +3 -3
  25. gemma_3_1B_LR_5e-4/config.json +3 -34
  26. gemma_3_1B_LR_5e-4/generation_config.json +3 -13
  27. gemma_3_1B_LR_5e-4/special_tokens_map.json +3 -33
  28. gemma_3_1B_LR_5e-4/tokenizer.json +3 -0
  29. gemma_3_1B_LR_5e-4/tokenizer_config.json +0 -0
  30. gemma_3_1B_LR_5e-5/added_tokens.json +3 -3
  31. gemma_3_1B_LR_5e-5/config.json +3 -34
  32. gemma_3_1B_LR_5e-5/generation_config.json +3 -13
  33. gemma_3_1B_LR_5e-5/special_tokens_map.json +3 -33
  34. gemma_3_1B_LR_5e-5/tokenizer.json +3 -0
  35. gemma_3_1B_LR_5e-5/tokenizer_config.json +0 -0
  36. gemma_3_4b_LR_1e-4/added_tokens.json +3 -3
  37. gemma_3_4b_LR_1e-4/config.json +3 -58
  38. gemma_3_4b_LR_1e-4/generation_config.json +3 -13
  39. gemma_3_4b_LR_1e-4/pytorch_model.bin.index.json +3 -891
  40. gemma_3_4b_LR_1e-4/special_tokens_map.json +3 -33
  41. gemma_3_4b_LR_1e-4/tokenizer.json +3 -0
  42. gemma_3_4b_LR_1e-4/tokenizer_config.json +0 -0
  43. gemma_3_4b_LR_5e-5/added_tokens.json +3 -3
  44. gemma_3_4b_LR_5e-5/config.json +3 -58
  45. gemma_3_4b_LR_5e-5/generation_config.json +3 -13
  46. gemma_3_4b_LR_5e-5/pytorch_model.bin.index.json +3 -891
  47. gemma_3_4b_LR_5e-5/special_tokens_map.json +3 -33
  48. gemma_3_4b_LR_5e-5/tokenizer.json +3 -0
  49. gemma_3_4b_LR_5e-5/tokenizer_config.json +0 -0
gemma_3_1B_LR_1e-3/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_1e-3/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-3/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-3/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-3/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_1B_LR_1e-4/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_1e-4/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-4/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-4/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_1B_LR_1e-4/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_1B_LR_1e-5/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_1e-5/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-5/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-5/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_1e-5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_1B_LR_1e-5/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_1B_LR_5e-3/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_5e-3/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-3/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-3/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-3/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_1B_LR_5e-3/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_1B_LR_5e-4/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_5e-4/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-4/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-4/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_1B_LR_5e-4/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_1B_LR_5e-5/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_1B_LR_5e-5/config.json CHANGED
@@ -1,34 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.52.4",
32
- "use_cache": true,
33
- "vocab_size": 262152
34
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a12baa48a29c3f76d0a086782ebe8958c4b39eb12cb6370e3b13bcd66f2e19f
3
+ size 875
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-5/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-5/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_1B_LR_5e-5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_1B_LR_5e-5/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_4b_LR_1e-4/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_4b_LR_1e-4/config.json CHANGED
@@ -1,58 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
- ],
5
- "boi_token_index": 255999,
6
- "eoi_token_index": 256000,
7
- "image_token_index": 262144,
8
- "initializer_range": 0.02,
9
- "mm_tokens_per_image": 256,
10
- "model_type": "gemma3",
11
- "text_config": {
12
- "attention_bias": false,
13
- "attention_dropout": 0.0,
14
- "attn_logit_softcapping": null,
15
- "cache_implementation": "hybrid",
16
- "final_logit_softcapping": null,
17
- "head_dim": 256,
18
- "hidden_activation": "gelu_pytorch_tanh",
19
- "hidden_size": 2560,
20
- "initializer_range": 0.02,
21
- "intermediate_size": 10240,
22
- "max_position_embeddings": 131072,
23
- "model_type": "gemma3_text",
24
- "num_attention_heads": 8,
25
- "num_hidden_layers": 34,
26
- "num_key_value_heads": 4,
27
- "query_pre_attn_scalar": 256,
28
- "rms_norm_eps": 1e-06,
29
- "rope_local_base_freq": 10000.0,
30
- "rope_scaling": {
31
- "factor": 8.0,
32
- "rope_type": "linear"
33
- },
34
- "rope_theta": 1000000.0,
35
- "sliding_window": 1024,
36
- "sliding_window_pattern": 6,
37
- "torch_dtype": "bfloat16",
38
- "use_cache": true,
39
- "vocab_size": 262208
40
- },
41
- "torch_dtype": "bfloat16",
42
- "transformers_version": "4.52.4",
43
- "vision_config": {
44
- "attention_dropout": 0.0,
45
- "hidden_act": "gelu_pytorch_tanh",
46
- "hidden_size": 1152,
47
- "image_size": 896,
48
- "intermediate_size": 4304,
49
- "layer_norm_eps": 1e-06,
50
- "model_type": "siglip_vision_model",
51
- "num_attention_heads": 16,
52
- "num_channels": 3,
53
- "num_hidden_layers": 27,
54
- "patch_size": 14,
55
- "torch_dtype": "bfloat16",
56
- "vision_use_head": false
57
- }
58
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9c50d85b67b24d3d6daafd287865337156397179d56783833c40746acc81c2
3
+ size 1569
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_1e-4/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_1e-4/pytorch_model.bin.index.json CHANGED
@@ -1,891 +1,3 @@
1
- {
2
- "metadata": {
3
- "total_size": 8600158944
4
- },
5
- "weight_map": {
6
- "language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
- "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
- "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
- "language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
- "language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
- "language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
16
- "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
17
- "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
18
- "language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
19
- "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
20
- "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
21
- "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
- "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
23
- "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
24
- "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
25
- "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
- "language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
- "language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
28
- "language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
29
- "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
30
- "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
31
- "language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
32
- "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
33
- "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
34
- "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
- "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
36
- "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
37
- "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
38
- "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
- "language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
- "language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
- "language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
42
- "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
43
- "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
44
- "language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
45
- "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
- "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
47
- "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
- "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
49
- "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
50
- "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
51
- "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
52
- "language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
- "language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
- "language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
55
- "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
56
- "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
57
- "language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
58
- "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
59
- "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
60
- "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
61
- "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
62
- "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
63
- "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
64
- "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
65
- "language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
- "language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
- "language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
68
- "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
69
- "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
70
- "language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
71
- "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
72
- "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
73
- "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
74
- "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
75
- "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
76
- "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
77
- "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
78
- "language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
- "language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
- "language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
81
- "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
- "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
83
- "language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
84
- "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
85
- "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
86
- "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
87
- "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
88
- "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
89
- "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
90
- "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
91
- "language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
92
- "language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
- "language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
94
- "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
- "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
- "language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
97
- "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
98
- "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
99
- "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
100
- "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
101
- "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
102
- "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
103
- "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
104
- "language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
- "language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
106
- "language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
107
- "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
108
- "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
109
- "language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
110
- "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
111
- "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
112
- "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
113
- "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
114
- "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
115
- "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
116
- "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
- "language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
118
- "language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
119
- "language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
120
- "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
121
- "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
122
- "language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
123
- "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
124
- "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
125
- "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
- "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
127
- "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
128
- "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
129
- "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
- "language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
131
- "language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
- "language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
133
- "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
134
- "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
135
- "language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
136
- "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
137
- "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
138
- "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
139
- "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
140
- "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
141
- "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
142
- "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
143
- "language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
- "language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
145
- "language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
146
- "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
147
- "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
148
- "language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
149
- "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
150
- "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
151
- "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
152
- "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
153
- "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
154
- "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
- "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
- "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
- "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
158
- "language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
159
- "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
160
- "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
161
- "language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
162
- "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
163
- "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
164
- "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
- "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
166
- "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
167
- "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
168
- "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
- "language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
170
- "language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
- "language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
172
- "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
173
- "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
174
- "language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
175
- "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
- "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
177
- "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
178
- "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
179
- "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
180
- "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
181
- "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
182
- "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
- "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
- "language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
185
- "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
186
- "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
187
- "language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
188
- "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
189
- "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
190
- "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
191
- "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
192
- "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
193
- "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
194
- "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
195
- "language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
196
- "language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
197
- "language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
198
- "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
199
- "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
200
- "language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
201
- "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
202
- "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
203
- "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
204
- "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
205
- "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
206
- "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
207
- "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
208
- "language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
- "language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
210
- "language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
211
- "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
- "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
- "language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
214
- "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
215
- "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
216
- "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
217
- "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
218
- "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
219
- "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
220
- "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
221
- "language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
222
- "language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
- "language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
224
- "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
225
- "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
226
- "language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
227
- "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
228
- "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
229
- "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
230
- "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
231
- "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
232
- "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
233
- "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
- "language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
235
- "language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
236
- "language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
237
- "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
238
- "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
239
- "language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
240
- "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
- "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
- "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
243
- "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
244
- "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
245
- "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
246
- "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
247
- "language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
248
- "language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
- "language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
250
- "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
251
- "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
252
- "language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
253
- "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
254
- "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
255
- "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
256
- "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
257
- "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
258
- "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
259
- "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
260
- "language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
261
- "language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
262
- "language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
263
- "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
- "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
- "language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
266
- "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
267
- "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
- "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
269
- "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
270
- "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
271
- "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
272
- "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
273
- "language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
274
- "language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
275
- "language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
276
- "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
277
- "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
278
- "language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
279
- "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
280
- "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
281
- "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
282
- "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
283
- "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
284
- "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
285
- "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
286
- "language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
287
- "language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
288
- "language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
289
- "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
290
- "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
291
- "language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
292
- "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
293
- "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
294
- "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
295
- "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
296
- "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
297
- "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
298
- "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
299
- "language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
300
- "language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
301
- "language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
302
- "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
303
- "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
304
- "language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
305
- "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
306
- "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
307
- "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
308
- "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
309
- "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
310
- "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
311
- "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
312
- "language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
- "language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
314
- "language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
315
- "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
316
- "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
317
- "language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
318
- "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
319
- "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
320
- "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
321
- "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
322
- "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
323
- "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
324
- "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
325
- "language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
326
- "language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
327
- "language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
328
- "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
329
- "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
330
- "language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
331
- "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
332
- "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
333
- "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
334
- "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
335
- "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
336
- "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
337
- "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
338
- "language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
339
- "language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
340
- "language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
341
- "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
342
- "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
343
- "language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
344
- "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
345
- "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
346
- "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
347
- "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
348
- "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
349
- "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
350
- "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
351
- "language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
352
- "language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
353
- "language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
354
- "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
355
- "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
356
- "language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
357
- "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
358
- "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
359
- "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
360
- "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
361
- "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
362
- "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
363
- "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
364
- "language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
365
- "language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
366
- "language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
367
- "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
368
- "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
369
- "language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
370
- "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
371
- "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
372
- "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
373
- "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
374
- "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
375
- "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
376
- "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
377
- "language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
378
- "language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
379
- "language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
380
- "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
381
- "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
382
- "language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
383
- "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
384
- "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
385
- "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
386
- "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
387
- "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
388
- "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
389
- "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
390
- "language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
391
- "language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
392
- "language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
393
- "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
394
- "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
395
- "language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
396
- "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
397
- "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
398
- "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
399
- "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
400
- "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
401
- "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
402
- "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
403
- "language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
404
- "language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
405
- "language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
406
- "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
407
- "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
408
- "language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
409
- "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
410
- "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
411
- "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
412
- "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
413
- "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
414
- "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
415
- "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
416
- "language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
417
- "language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
418
- "language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
419
- "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
420
- "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
421
- "language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
422
- "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
423
- "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
424
- "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
425
- "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
426
- "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
427
- "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
428
- "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
429
- "language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
430
- "language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
431
- "language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
432
- "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
433
- "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
434
- "language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
435
- "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
436
- "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
437
- "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
438
- "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
439
- "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
440
- "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
441
- "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
442
- "language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
443
- "language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
444
- "language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
445
- "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
446
- "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
447
- "language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
448
- "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
449
- "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
450
- "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
451
- "multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
452
- "multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
453
- "vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
454
- "vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
455
- "vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
456
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
457
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
458
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
459
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
460
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
461
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
462
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
463
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
464
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
465
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
466
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
467
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
468
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
469
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
470
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
471
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
472
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
473
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
474
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
475
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
476
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
477
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
478
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
479
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
480
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
481
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
482
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
483
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
484
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
485
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
486
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
487
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
488
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
489
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
490
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
491
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
492
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
493
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
494
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
495
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
496
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
497
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
498
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
499
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
500
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
501
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
502
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
503
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
504
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
505
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
506
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
507
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
508
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
509
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
510
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
511
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
512
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
513
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
514
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
515
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
516
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
517
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
518
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
519
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
520
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
521
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
522
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
523
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
524
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
525
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
526
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
527
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
528
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
529
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
530
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
531
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
532
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
533
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
534
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
535
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
536
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
537
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
538
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
539
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
540
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
541
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
542
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
543
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
544
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
545
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
546
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
547
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
548
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
549
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
550
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
551
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
552
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
553
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
554
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
555
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
556
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
557
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
558
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
559
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
560
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
561
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
562
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
563
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
564
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
565
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
566
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
567
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
568
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
569
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
570
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
571
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
572
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
573
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
574
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
575
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
576
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
577
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
578
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
579
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
580
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
581
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
582
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
583
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
584
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
585
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
586
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
587
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
588
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
589
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
590
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
591
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
592
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
593
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
594
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
595
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
596
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
597
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
598
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
599
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
600
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
601
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
602
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
603
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
604
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
605
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
606
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
607
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
608
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
609
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
610
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
611
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
612
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
613
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
614
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
615
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
616
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
617
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
618
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
619
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
620
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
621
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
622
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
623
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
624
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
625
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
626
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
627
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
628
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
629
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
630
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
631
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
632
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
633
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
634
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
635
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
636
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
637
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
638
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
639
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
640
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
641
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
642
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
643
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
644
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
645
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
646
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
647
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
648
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
649
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
650
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
651
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
652
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
653
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
654
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
655
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
656
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
657
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
658
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
659
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
660
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
661
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
662
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
663
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
664
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
665
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
666
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
667
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
668
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
669
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
670
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
671
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
672
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
673
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
674
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
675
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
676
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
677
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
678
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
679
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
680
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
681
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
682
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
683
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
684
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
685
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
686
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
687
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
688
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
689
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
690
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
691
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
692
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
693
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
694
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
695
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
696
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
697
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
698
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
699
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
700
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
701
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
702
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
703
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
704
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
705
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
706
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
707
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
708
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
709
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
710
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
711
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
712
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
713
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
714
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
715
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
716
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
717
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
718
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
719
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
720
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
721
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
722
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
723
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
724
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
725
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
726
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
727
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
728
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
729
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
730
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
731
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
732
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
733
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
734
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
735
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
736
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
737
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
738
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
739
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
740
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
741
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
742
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
743
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
744
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
745
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
746
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
747
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
748
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
749
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
750
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
751
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
752
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
753
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
754
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
755
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
756
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
757
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
758
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
759
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
760
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
761
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
762
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
763
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
764
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
765
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
766
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
767
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
768
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
769
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
770
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
771
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
772
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
773
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
774
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
775
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
776
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
777
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
778
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
779
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
780
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
781
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
782
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
783
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
784
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
785
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
786
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
787
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
788
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
789
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
790
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
791
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
792
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
793
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
794
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
795
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
796
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
797
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
798
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
799
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
800
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
801
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
802
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
803
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
804
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
805
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
806
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
807
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
808
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
809
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
810
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
811
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
812
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
813
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
814
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
815
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
816
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
817
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
818
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
819
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
820
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
821
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
822
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
823
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
824
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
825
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
826
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
827
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
828
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
829
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
830
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
831
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
832
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
833
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
834
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
835
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
836
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
837
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
838
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
839
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
840
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
841
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
842
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
843
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
844
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
845
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
846
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
847
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
848
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
849
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
850
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
851
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
852
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
853
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
854
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
855
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
856
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
857
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
858
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
859
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
860
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
861
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
862
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
863
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
864
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
865
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
866
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
867
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
868
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
869
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
870
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
871
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
872
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
873
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
874
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
875
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
876
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
877
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
878
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
879
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
880
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
881
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
882
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
883
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
884
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
885
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
886
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
887
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
888
- "vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
889
- "vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
890
- }
891
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445f609e3601a9ed71c896883269d7ec948f7a0586538210c9b47ae625fd90c2
3
+ size 90631
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_1e-4/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_1e-4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_4b_LR_1e-4/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
gemma_3_4b_LR_5e-5/added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946
3
+ size 35
gemma_3_4b_LR_5e-5/config.json CHANGED
@@ -1,58 +1,3 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
- ],
5
- "boi_token_index": 255999,
6
- "eoi_token_index": 256000,
7
- "image_token_index": 262144,
8
- "initializer_range": 0.02,
9
- "mm_tokens_per_image": 256,
10
- "model_type": "gemma3",
11
- "text_config": {
12
- "attention_bias": false,
13
- "attention_dropout": 0.0,
14
- "attn_logit_softcapping": null,
15
- "cache_implementation": "hybrid",
16
- "final_logit_softcapping": null,
17
- "head_dim": 256,
18
- "hidden_activation": "gelu_pytorch_tanh",
19
- "hidden_size": 2560,
20
- "initializer_range": 0.02,
21
- "intermediate_size": 10240,
22
- "max_position_embeddings": 131072,
23
- "model_type": "gemma3_text",
24
- "num_attention_heads": 8,
25
- "num_hidden_layers": 34,
26
- "num_key_value_heads": 4,
27
- "query_pre_attn_scalar": 256,
28
- "rms_norm_eps": 1e-06,
29
- "rope_local_base_freq": 10000.0,
30
- "rope_scaling": {
31
- "factor": 8.0,
32
- "rope_type": "linear"
33
- },
34
- "rope_theta": 1000000.0,
35
- "sliding_window": 1024,
36
- "sliding_window_pattern": 6,
37
- "torch_dtype": "bfloat16",
38
- "use_cache": true,
39
- "vocab_size": 262208
40
- },
41
- "torch_dtype": "bfloat16",
42
- "transformers_version": "4.52.4",
43
- "vision_config": {
44
- "attention_dropout": 0.0,
45
- "hidden_act": "gelu_pytorch_tanh",
46
- "hidden_size": 1152,
47
- "image_size": 896,
48
- "intermediate_size": 4304,
49
- "layer_norm_eps": 1e-06,
50
- "model_type": "siglip_vision_model",
51
- "num_attention_heads": 16,
52
- "num_channels": 3,
53
- "num_hidden_layers": 27,
54
- "patch_size": 14,
55
- "torch_dtype": "bfloat16",
56
- "vision_use_head": false
57
- }
58
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9c50d85b67b24d3d6daafd287865337156397179d56783833c40746acc81c2
3
+ size 1569
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_5e-5/generation_config.json CHANGED
@@ -1,13 +1,3 @@
1
- {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 1,
7
- 106
8
- ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.4"
13
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd67fde34eaea6590a20d3b4083eac762561921172ca8f411fe4daf052cba2da
3
+ size 210
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_5e-5/pytorch_model.bin.index.json CHANGED
@@ -1,891 +1,3 @@
1
- {
2
- "metadata": {
3
- "total_size": 8600158944
4
- },
5
- "weight_map": {
6
- "language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
- "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
- "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
- "language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
- "language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
- "language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
16
- "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
17
- "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
18
- "language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
19
- "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
20
- "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
21
- "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
- "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
23
- "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
24
- "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
25
- "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
- "language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
- "language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
28
- "language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
29
- "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
30
- "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
31
- "language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
32
- "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
33
- "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
34
- "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
- "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
36
- "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
37
- "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
38
- "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
- "language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
- "language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
- "language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
42
- "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
43
- "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
44
- "language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
45
- "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
46
- "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
47
- "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
- "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
49
- "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
50
- "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
51
- "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
52
- "language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
- "language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
- "language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
55
- "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
56
- "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
57
- "language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
58
- "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
59
- "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
60
- "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
61
- "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
62
- "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
63
- "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
64
- "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
65
- "language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
- "language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
- "language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
68
- "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
69
- "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
70
- "language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
71
- "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
72
- "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
73
- "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
74
- "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
75
- "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
76
- "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
77
- "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
78
- "language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
- "language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
- "language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
81
- "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
82
- "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
83
- "language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
84
- "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
85
- "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
86
- "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
87
- "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
88
- "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
89
- "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
90
- "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
91
- "language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
92
- "language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
- "language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
94
- "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
- "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
- "language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
97
- "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
98
- "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
99
- "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
100
- "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
101
- "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
102
- "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
103
- "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
104
- "language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
- "language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
106
- "language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
107
- "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
108
- "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
109
- "language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
110
- "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
111
- "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
112
- "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
113
- "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
114
- "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
115
- "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
116
- "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
- "language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
118
- "language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
119
- "language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
120
- "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
121
- "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
122
- "language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
123
- "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
124
- "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
125
- "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
- "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
127
- "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
128
- "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
129
- "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
- "language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
131
- "language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
- "language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
133
- "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
134
- "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
135
- "language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
136
- "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
137
- "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
138
- "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
139
- "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
140
- "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
141
- "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
142
- "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
143
- "language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
- "language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
145
- "language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
146
- "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
147
- "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
148
- "language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
149
- "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
150
- "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
151
- "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
152
- "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
153
- "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
154
- "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
- "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
- "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
- "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
158
- "language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
159
- "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
160
- "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
161
- "language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
162
- "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
163
- "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
164
- "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
- "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
166
- "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
167
- "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
168
- "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
169
- "language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
170
- "language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
- "language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
172
- "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
173
- "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
174
- "language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
175
- "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
176
- "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
177
- "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
178
- "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
179
- "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
180
- "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
181
- "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
182
- "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
- "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
- "language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
185
- "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
186
- "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
187
- "language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
188
- "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
189
- "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
190
- "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
191
- "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
192
- "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
193
- "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
194
- "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
195
- "language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
196
- "language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
197
- "language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
198
- "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
199
- "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
200
- "language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
201
- "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
202
- "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
203
- "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
204
- "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
205
- "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
206
- "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
207
- "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
208
- "language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
- "language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
210
- "language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
211
- "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
- "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
- "language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
214
- "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
215
- "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
216
- "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
217
- "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
218
- "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
219
- "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
220
- "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
221
- "language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
222
- "language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
- "language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
224
- "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
225
- "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
226
- "language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
227
- "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
228
- "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
229
- "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
230
- "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
231
- "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
232
- "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
233
- "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
- "language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
235
- "language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
236
- "language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
237
- "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
238
- "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
239
- "language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
240
- "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
- "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
- "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
243
- "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
244
- "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
245
- "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
246
- "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
247
- "language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
248
- "language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
- "language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
250
- "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
251
- "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
252
- "language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
253
- "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
254
- "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
255
- "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
256
- "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
257
- "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
258
- "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
259
- "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
260
- "language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
261
- "language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
262
- "language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
263
- "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
264
- "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
265
- "language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
266
- "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
267
- "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
268
- "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
269
- "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
270
- "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
271
- "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
272
- "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
273
- "language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
274
- "language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
275
- "language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
276
- "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
277
- "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
278
- "language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
279
- "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
280
- "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
281
- "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
282
- "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
283
- "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
284
- "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
285
- "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
286
- "language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
287
- "language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
288
- "language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
289
- "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
290
- "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
291
- "language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
292
- "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
293
- "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
294
- "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
295
- "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
296
- "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
297
- "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
298
- "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
299
- "language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
300
- "language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
301
- "language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
302
- "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
303
- "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
304
- "language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
305
- "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
306
- "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
307
- "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
308
- "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
309
- "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
310
- "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
311
- "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
312
- "language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
- "language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
314
- "language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
315
- "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
316
- "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
317
- "language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
318
- "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
319
- "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
320
- "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
321
- "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
322
- "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
323
- "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
324
- "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
325
- "language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
326
- "language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
327
- "language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
328
- "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
329
- "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
330
- "language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
331
- "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
332
- "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
333
- "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
334
- "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
335
- "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
336
- "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
337
- "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
338
- "language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
339
- "language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
340
- "language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
341
- "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
342
- "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
343
- "language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
344
- "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
345
- "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
346
- "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
347
- "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
348
- "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
349
- "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
350
- "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
351
- "language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
352
- "language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
353
- "language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
354
- "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
355
- "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
356
- "language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
357
- "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
358
- "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
359
- "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
360
- "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
361
- "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
362
- "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
363
- "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
364
- "language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
365
- "language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
366
- "language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
367
- "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
368
- "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
369
- "language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
370
- "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
371
- "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
372
- "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
373
- "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
374
- "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
375
- "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
376
- "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
377
- "language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
378
- "language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
379
- "language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
380
- "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
381
- "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
382
- "language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
383
- "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
384
- "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
385
- "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
386
- "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
387
- "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
388
- "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
389
- "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
390
- "language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
391
- "language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
392
- "language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
393
- "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
394
- "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
395
- "language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
396
- "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
397
- "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
398
- "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
399
- "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
400
- "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
401
- "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
402
- "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
403
- "language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
404
- "language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
405
- "language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
406
- "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
407
- "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
408
- "language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
409
- "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
410
- "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
411
- "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
412
- "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
413
- "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
414
- "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
415
- "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
416
- "language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
417
- "language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
418
- "language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
419
- "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
420
- "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
421
- "language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
422
- "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
423
- "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
424
- "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
425
- "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
426
- "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
427
- "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
428
- "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
429
- "language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
430
- "language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
431
- "language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
432
- "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
433
- "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
434
- "language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
435
- "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
436
- "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
437
- "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
438
- "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
439
- "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
440
- "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
441
- "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
442
- "language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
443
- "language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
444
- "language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
445
- "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
446
- "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
447
- "language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
448
- "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
449
- "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
450
- "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
451
- "multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
452
- "multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
453
- "vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
454
- "vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
455
- "vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
456
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
457
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
458
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
459
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
460
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
461
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
462
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
463
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
464
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
465
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
466
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
467
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
468
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
469
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
470
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
471
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
472
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
473
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
474
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
475
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
476
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
477
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
478
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
479
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
480
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
481
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
482
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
483
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
484
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
485
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
486
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
487
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
488
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
489
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
490
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
491
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
492
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
493
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
494
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
495
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
496
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
497
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
498
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
499
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
500
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
501
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
502
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
503
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
504
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
505
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
506
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
507
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
508
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
509
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
510
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
511
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
512
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
513
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
514
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
515
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
516
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
517
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
518
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
519
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
520
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
521
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
522
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
523
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
524
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
525
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
526
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
527
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
528
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
529
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
530
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
531
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
532
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
533
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
534
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
535
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
536
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
537
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
538
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
539
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
540
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
541
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
542
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
543
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
544
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
545
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
546
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
547
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
548
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
549
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
550
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
551
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
552
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
553
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
554
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
555
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
556
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
557
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
558
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
559
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
560
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
561
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
562
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
563
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
564
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
565
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
566
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
567
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
568
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
569
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
570
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
571
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
572
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
573
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
574
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
575
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
576
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
577
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
578
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
579
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
580
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
581
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
582
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
583
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
584
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
585
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
586
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
587
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
588
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
589
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
590
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
591
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
592
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
593
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
594
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
595
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
596
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
597
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
598
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
599
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
600
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
601
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
602
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
603
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
604
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
605
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
606
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
607
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
608
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
609
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
610
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
611
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
612
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
613
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
614
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
615
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
616
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
617
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
618
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
619
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
620
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
621
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
622
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
623
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
624
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
625
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
626
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
627
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
628
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
629
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
630
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
631
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
632
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
633
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
634
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
635
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
636
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
637
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
638
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
639
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
640
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
641
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
642
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
643
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
644
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
645
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
646
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
647
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
648
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
649
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
650
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
651
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
652
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
653
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
654
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
655
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
656
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
657
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
658
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
659
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
660
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
661
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
662
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
663
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
664
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
665
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
666
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
667
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
668
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
669
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
670
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
671
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
672
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
673
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
674
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
675
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
676
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
677
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
678
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
679
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
680
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
681
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
682
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
683
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
684
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
685
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
686
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
687
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
688
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
689
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
690
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
691
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
692
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
693
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
694
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
695
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
696
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
697
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
698
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
699
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
700
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
701
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
702
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
703
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
704
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
705
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
706
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
707
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
708
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
709
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
710
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
711
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
712
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
713
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
714
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
715
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
716
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
717
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
718
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
719
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
720
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
721
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
722
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
723
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
724
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
725
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
726
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
727
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
728
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
729
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
730
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
731
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
732
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
733
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
734
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
735
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
736
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
737
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
738
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
739
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
740
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
741
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
742
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
743
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
744
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
745
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
746
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
747
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
748
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
749
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
750
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
751
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
752
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
753
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
754
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
755
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
756
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
757
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
758
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
759
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
760
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
761
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
762
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
763
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
764
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
765
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
766
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
767
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
768
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
769
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
770
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
771
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
772
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
773
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
774
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
775
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
776
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
777
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
778
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
779
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
780
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
781
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
782
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
783
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
784
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
785
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
786
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
787
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
788
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
789
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
790
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
791
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
792
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
793
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
794
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
795
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
796
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
797
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
798
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
799
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
800
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
801
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
802
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
803
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
804
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
805
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
806
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
807
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
808
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
809
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
810
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
811
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
812
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
813
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
814
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
815
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
816
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
817
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
818
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
819
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
820
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
821
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
822
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
823
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
824
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
825
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
826
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
827
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
828
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
829
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
830
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
831
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
832
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
833
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
834
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
835
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
836
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
837
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
838
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
839
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
840
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
841
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
842
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
843
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
844
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
845
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
846
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
847
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
848
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
849
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
850
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
851
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
852
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
853
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
854
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
855
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
856
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
857
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
858
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
859
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
860
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
861
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
862
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
863
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
864
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
865
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
866
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
867
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
868
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
869
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
870
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
871
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
872
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
873
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
874
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
875
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
876
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
877
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
878
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
879
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
880
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
881
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
882
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
883
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
884
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
885
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
886
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
887
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
888
- "vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
889
- "vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
890
- }
891
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445f609e3601a9ed71c896883269d7ec948f7a0586538210c9b47ae625fd90c2
3
+ size 90631
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_5e-5/special_tokens_map.json CHANGED
@@ -1,33 +1,3 @@
1
- {
2
- "boi_token": "<start_of_image>",
3
- "bos_token": {
4
- "content": "<bos>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "eoi_token": "<end_of_image>",
11
- "eos_token": {
12
- "content": "<eos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "image_token": "<image_soft_token>",
19
- "pad_token": {
20
- "content": "<pad>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397
3
+ size 662
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gemma_3_4b_LR_5e-5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma_3_4b_LR_5e-5/tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff