Hugging Face's logo

IranQin
/
MineLLM

Model card Files Community
IranQin commited on
Commit
030971f
•
1 Parent(s): 0803a01

Configure LFS and re-add files

Browse files
Files changed (48) hide show
  1. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/config.json +26 -0
  2. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model.pt +3 -0
  3. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt +3 -0
  4. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt +3 -0
  5. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt +3 -0
  6. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/special_tokens_map.json +24 -0
  7. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/tokenizer.model +3 -0
  8. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/tokenizer_config.json +35 -0
  9. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/config.json +26 -0
  10. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model.pt +3 -0
  11. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep1.pt +3 -0
  12. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep2.pt +3 -0
  13. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep3.pt +3 -0
  14. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/special_tokens_map.json +24 -0
  15. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/tokenizer.model +3 -0
  16. Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/tokenizer_config.json +35 -0
  17. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/config.json +26 -0
  18. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model.pt +3 -0
  19. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt +3 -0
  20. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt +3 -0
  21. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt +3 -0
  22. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/special_tokens_map.json +24 -0
  23. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/tokenizer.model +3 -0
  24. Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/tokenizer_config.json +35 -0
  25. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/config.json +27 -0
  26. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model.pt +3 -0
  27. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt +3 -0
  28. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt +3 -0
  29. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt +3 -0
  30. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/special_tokens_map.json +24 -0
  31. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer.model +3 -0
  32. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer_config.json +36 -0
  33. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/config.json +27 -0
  34. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model.pt +3 -0
  35. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep1.pt +3 -0
  36. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep2.pt +3 -0
  37. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep3.pt +3 -0
  38. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/special_tokens_map.json +24 -0
  39. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/tokenizer.model +3 -0
  40. Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/tokenizer_config.json +36 -0
  41. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/config.json +29 -0
  42. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model.pt +3 -0
  43. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt +3 -0
  44. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt +3 -0
  45. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt +3 -0
  46. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/special_tokens_map.json +24 -0
  47. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer.model +3 -0
  48. Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer_config.json +43 -0
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/llama2_ckpt/13b_chat/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d8e2aa10dc067287c7c84405da0e347d95d58f16c545da00c78268ede5ed38
3
+ size 165228971
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0a710e53379a07ece0bb018a5a52d9e8a3857afae42828d3254d2a41632518
3
+ size 165228971
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ffb954dfb025fae98a98043ee8a22c186525b35d071026ec84ae0aafaf98cf
3
+ size 165228971
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d8e2aa10dc067287c7c84405da0e347d95d58f16c545da00c78268ede5ed38
3
+ size 165228971
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_fast": false
35
+ }
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/llama2_ckpt/13b_chat/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b146de7dbd768b40003dfb95bc3d2897be2f027bf7240da775bbc7fc2df87d35
3
+ size 167850411
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d798ab498dc9f312f9429fc5079c8e78ff5ab1caee29d9a791a29b41044f902e
3
+ size 167850411
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5792289f658fa54e06d535324e794ed066c5cb3df92017a8c9eaafda715e92
3
+ size 167850411
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b146de7dbd768b40003dfb95bc3d2897be2f027bf7240da775bbc7fc2df87d35
3
+ size 167850411
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_LLaMA2_13b_chat_epoch_3_mlp2x_gelu_clip/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_fast": false
35
+ }
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/llama2_ckpt/7b_chat/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d09f70d0d835522434993f8509d13559bfa67f114238822db5fd829d469d91c
3
+ size 107017387
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd7666a62e29830c030fb94493a0c2ad24cad657b415a8ea93bf160fb17409c
3
+ size 107017387
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fbe4d1dd2b172e20f8f79733f1c888de684cd709425d550d68637ce84b3260
3
+ size 107017387
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d09f70d0d835522434993f8509d13559bfa67f114238822db5fd829d469d91c
3
+ size 107017387
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_LLaMA2_7b_chat_epoch_3_mlp2x_gelu/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_fast": false
35
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/vicuna_ckpt/13b_v1.5/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_length": 4096,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.31.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d248fbae4d47652f4863a1bfd2ec46081fc2f8a02b3de2cd1078e2209b16ee7
3
+ size 165228971
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a7d9d0d959dc41944c2bb294a5d7ec4872f069c4c15c4841387a547c303f48
3
+ size 165228971
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7da5d915ceeaafe671f19a62d5554fa7b3b8e0e5683f798190ace2de9abf083
3
+ size 165228971
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d248fbae4d47652f4863a1bfd2ec46081fc2f8a02b3de2cd1078e2209b16ee7
3
+ size 165228971
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "use_fast": false
36
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/vicuna_ckpt/13b_v1.5/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_length": 4096,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.31.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9a33d5b34251e1d62f72bfb033dd67296ff621ebb8071316454bb6ebe22f00
3
+ size 167850411
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628835cd779266b7001f42bc3bf9fa99c6dde10338f6b9f1f24badc82d9cf14d
3
+ size 167850411
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d615972174e6d1d5221cfa6c34d9850a8737ab08449deac25fef309eb08b5251
3
+ size 167850411
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9a33d5b34251e1d62f72bfb033dd67296ff621ebb8071316454bb6ebe22f00
3
+ size 167850411
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu_clip/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "use_fast": false
36
+ }
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../model_zoo/vicuna_ckpt/13b_v1.5/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_length": 4096,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.35.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689b99423df7ae304d0b03dd54b82e2d47623b7d420bd9bd7ab80c5f1cacdc40
3
+ size 165228971
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb24984b17055c0b1531345c542318621daf0ae655a807d56b2aed19eded40d9
3
+ size 165228971
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9320775015652836cebc97b1962e04b0abe6916ff52942bd375cb8ce5e60274
3
+ size 165228971
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/pytorch_model_ep3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689b99423df7ae304d0b03dd54b82e2d47623b7d420bd9bd7ab80c5f1cacdc40
3
+ size 165228971
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
Mine_52k_caption_Vicuna_13b_v1.5_epoch_3_mlp2x_gelu/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 4096,
35
+ "pad_token": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": false
43
+ }