Upload folder using huggingface_hub
Browse files- checkpoint-235000/config.json +45 -0
- checkpoint-235000/model.safetensors +3 -0
- checkpoint-235000/optimizer.pt +3 -0
- checkpoint-235000/rng_state.pth +3 -0
- checkpoint-235000/scheduler.pt +3 -0
- checkpoint-235000/special_tokens_map.json +51 -0
- checkpoint-235000/tokenizer.json +0 -0
- checkpoint-235000/tokenizer.model +3 -0
- checkpoint-235000/tokenizer_config.json +171 -0
- checkpoint-235000/trainer_state.json +0 -0
- checkpoint-235000/training_args.bin +3 -0
- checkpoint-285000/config.json +45 -0
- checkpoint-285000/model.safetensors +3 -0
- checkpoint-285000/optimizer.pt +3 -0
- checkpoint-285000/rng_state.pth +3 -0
- checkpoint-285000/scheduler.pt +3 -0
- checkpoint-285000/special_tokens_map.json +51 -0
- checkpoint-285000/tokenizer.json +0 -0
- checkpoint-285000/tokenizer.model +3 -0
- checkpoint-285000/tokenizer_config.json +171 -0
- checkpoint-285000/trainer_state.json +0 -0
- checkpoint-285000/training_args.bin +3 -0
- model.safetensors +1 -1
- tokenizer.json +2 -16
- training_args.bin +1 -1
checkpoint-235000/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "cls",
|
| 12 |
+
"cls_token_id": 6,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 2,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 256,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1024,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"local_attention": 128,
|
| 27 |
+
"local_rope_theta": 10000.0,
|
| 28 |
+
"max_position_embeddings": 8192,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"mlp_dropout": 0.0,
|
| 31 |
+
"model_type": "modernbert",
|
| 32 |
+
"norm_bias": false,
|
| 33 |
+
"norm_eps": 1e-05,
|
| 34 |
+
"num_attention_heads": 4,
|
| 35 |
+
"num_hidden_layers": 10,
|
| 36 |
+
"pad_token_id": 3,
|
| 37 |
+
"position_embedding_type": "rope",
|
| 38 |
+
"repad_logits_with_grad": false,
|
| 39 |
+
"sep_token_id": 4,
|
| 40 |
+
"sparse_pred_ignore_index": -100,
|
| 41 |
+
"sparse_prediction": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"vocab_size": 102400
|
| 45 |
+
}
|
checkpoint-235000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85be6777e1bdcafd4ef6a3faf62dcaf0904d018014734d348a8665b630303b3d
|
| 3 |
+
size 147501544
|
checkpoint-235000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed9af5b5090169a4ba588facb130c3bc33eff7ecb038bb60e8d2422cd263720
|
| 3 |
+
size 295044858
|
checkpoint-235000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af2454eb24723d86717ecfa847954e15cf4d543be7ec11a68c8f5e2f764a775a
|
| 3 |
+
size 14244
|
checkpoint-235000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91cb2bbd3e3402335496f5ae4c27b9b9a2596d2afacd1256fc3f0a66705b6266
|
| 3 |
+
size 1064
|
checkpoint-235000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<cls>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "<sep>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-235000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-235000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
|
| 3 |
+
size 1831879
|
checkpoint-235000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_dummy_prefix_space": false,
|
| 4 |
+
"add_eos_token": true,
|
| 5 |
+
"add_prefix_space": false,
|
| 6 |
+
"added_tokens_decoder": {
|
| 7 |
+
"0": {
|
| 8 |
+
"content": "<unk>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
"1": {
|
| 16 |
+
"content": "<s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"special": true
|
| 22 |
+
},
|
| 23 |
+
"2": {
|
| 24 |
+
"content": "</s>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false,
|
| 29 |
+
"special": true
|
| 30 |
+
},
|
| 31 |
+
"3": {
|
| 32 |
+
"content": "<pad>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"special": true
|
| 38 |
+
},
|
| 39 |
+
"4": {
|
| 40 |
+
"content": "<sep>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
"5": {
|
| 48 |
+
"content": "<mask>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": false,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"special": true
|
| 54 |
+
},
|
| 55 |
+
"6": {
|
| 56 |
+
"content": "<cls>",
|
| 57 |
+
"lstrip": false,
|
| 58 |
+
"normalized": false,
|
| 59 |
+
"rstrip": false,
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"special": true
|
| 62 |
+
},
|
| 63 |
+
"7": {
|
| 64 |
+
"content": "<|system|>",
|
| 65 |
+
"lstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"rstrip": false,
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"special": false
|
| 70 |
+
},
|
| 71 |
+
"8": {
|
| 72 |
+
"content": "<|assistant|>",
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"normalized": false,
|
| 75 |
+
"rstrip": false,
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"special": false
|
| 78 |
+
},
|
| 79 |
+
"9": {
|
| 80 |
+
"content": "<|user|>",
|
| 81 |
+
"lstrip": false,
|
| 82 |
+
"normalized": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"special": false
|
| 86 |
+
},
|
| 87 |
+
"10": {
|
| 88 |
+
"content": "<|available_tools|>",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"special": false
|
| 94 |
+
},
|
| 95 |
+
"11": {
|
| 96 |
+
"content": "<|tool_calls|>",
|
| 97 |
+
"lstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"special": false
|
| 102 |
+
},
|
| 103 |
+
"12": {
|
| 104 |
+
"content": "<|tool_results|>",
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"normalized": false,
|
| 107 |
+
"rstrip": false,
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"special": false
|
| 110 |
+
},
|
| 111 |
+
"13": {
|
| 112 |
+
"content": "<|code|>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"special": false
|
| 118 |
+
},
|
| 119 |
+
"14": {
|
| 120 |
+
"content": "<|file|>",
|
| 121 |
+
"lstrip": false,
|
| 122 |
+
"normalized": false,
|
| 123 |
+
"rstrip": false,
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"special": false
|
| 126 |
+
},
|
| 127 |
+
"102397": {
|
| 128 |
+
"content": "<|prefix|>",
|
| 129 |
+
"lstrip": false,
|
| 130 |
+
"normalized": false,
|
| 131 |
+
"rstrip": false,
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"special": false
|
| 134 |
+
},
|
| 135 |
+
"102398": {
|
| 136 |
+
"content": "<|suffix|>",
|
| 137 |
+
"lstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"rstrip": false,
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"special": false
|
| 142 |
+
},
|
| 143 |
+
"102399": {
|
| 144 |
+
"content": "<|middle|>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"special": false
|
| 150 |
+
}
|
| 151 |
+
},
|
| 152 |
+
"bos_token": "<s>",
|
| 153 |
+
"clean_up_tokenization_spaces": false,
|
| 154 |
+
"cls_token": "<cls>",
|
| 155 |
+
"do_lower_case": false,
|
| 156 |
+
"eos_token": "</s>",
|
| 157 |
+
"extra_ids": 0,
|
| 158 |
+
"extra_special_tokens": {},
|
| 159 |
+
"keep_accents": true,
|
| 160 |
+
"legacy": false,
|
| 161 |
+
"mask_token": "<mask>",
|
| 162 |
+
"model_max_length": 8192,
|
| 163 |
+
"pad_token": "<pad>",
|
| 164 |
+
"padding_side": "right",
|
| 165 |
+
"sep_token": "<sep>",
|
| 166 |
+
"sp_model_kwargs": {},
|
| 167 |
+
"spaces_between_special_tokens": false,
|
| 168 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 169 |
+
"unk_token": "<unk>",
|
| 170 |
+
"use_default_system_prompt": false
|
| 171 |
+
}
|
checkpoint-235000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-235000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9160177d49df3f031ebcb090af2b1e306d3679081035ca8245b2ac268971306c
|
| 3 |
+
size 5304
|
checkpoint-285000/config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "cls",
|
| 12 |
+
"cls_token_id": 6,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 2,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 256,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1024,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"local_attention": 128,
|
| 27 |
+
"local_rope_theta": 10000.0,
|
| 28 |
+
"max_position_embeddings": 8192,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"mlp_dropout": 0.0,
|
| 31 |
+
"model_type": "modernbert",
|
| 32 |
+
"norm_bias": false,
|
| 33 |
+
"norm_eps": 1e-05,
|
| 34 |
+
"num_attention_heads": 4,
|
| 35 |
+
"num_hidden_layers": 10,
|
| 36 |
+
"pad_token_id": 3,
|
| 37 |
+
"position_embedding_type": "rope",
|
| 38 |
+
"repad_logits_with_grad": false,
|
| 39 |
+
"sep_token_id": 4,
|
| 40 |
+
"sparse_pred_ignore_index": -100,
|
| 41 |
+
"sparse_prediction": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"vocab_size": 102400
|
| 45 |
+
}
|
checkpoint-285000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62f492deafbdcdfcb5dd42da1620914482fb5c917a159dd6f5cd30e80f0e38d3
|
| 3 |
+
size 147501544
|
checkpoint-285000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbfefe8362841b57760f7b48b1c077d2575a4fe814152793754d04c06afe76bc
|
| 3 |
+
size 295044858
|
checkpoint-285000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89ec13c580ac7a383c50ebec392c73f3b90603bacca7129529467539857cb8ea
|
| 3 |
+
size 14244
|
checkpoint-285000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:089be5c030ca0ac155a1f4836a960ac3503cafd3d877472b114c1c7896092b27
|
| 3 |
+
size 1064
|
checkpoint-285000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<cls>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "<sep>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-285000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-285000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
|
| 3 |
+
size 1831879
|
checkpoint-285000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_dummy_prefix_space": false,
|
| 4 |
+
"add_eos_token": true,
|
| 5 |
+
"add_prefix_space": false,
|
| 6 |
+
"added_tokens_decoder": {
|
| 7 |
+
"0": {
|
| 8 |
+
"content": "<unk>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
"1": {
|
| 16 |
+
"content": "<s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"special": true
|
| 22 |
+
},
|
| 23 |
+
"2": {
|
| 24 |
+
"content": "</s>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false,
|
| 29 |
+
"special": true
|
| 30 |
+
},
|
| 31 |
+
"3": {
|
| 32 |
+
"content": "<pad>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"special": true
|
| 38 |
+
},
|
| 39 |
+
"4": {
|
| 40 |
+
"content": "<sep>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
"5": {
|
| 48 |
+
"content": "<mask>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": false,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"special": true
|
| 54 |
+
},
|
| 55 |
+
"6": {
|
| 56 |
+
"content": "<cls>",
|
| 57 |
+
"lstrip": false,
|
| 58 |
+
"normalized": false,
|
| 59 |
+
"rstrip": false,
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"special": true
|
| 62 |
+
},
|
| 63 |
+
"7": {
|
| 64 |
+
"content": "<|system|>",
|
| 65 |
+
"lstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"rstrip": false,
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"special": false
|
| 70 |
+
},
|
| 71 |
+
"8": {
|
| 72 |
+
"content": "<|assistant|>",
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"normalized": false,
|
| 75 |
+
"rstrip": false,
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"special": false
|
| 78 |
+
},
|
| 79 |
+
"9": {
|
| 80 |
+
"content": "<|user|>",
|
| 81 |
+
"lstrip": false,
|
| 82 |
+
"normalized": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"special": false
|
| 86 |
+
},
|
| 87 |
+
"10": {
|
| 88 |
+
"content": "<|available_tools|>",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"special": false
|
| 94 |
+
},
|
| 95 |
+
"11": {
|
| 96 |
+
"content": "<|tool_calls|>",
|
| 97 |
+
"lstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"rstrip": false,
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"special": false
|
| 102 |
+
},
|
| 103 |
+
"12": {
|
| 104 |
+
"content": "<|tool_results|>",
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"normalized": false,
|
| 107 |
+
"rstrip": false,
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"special": false
|
| 110 |
+
},
|
| 111 |
+
"13": {
|
| 112 |
+
"content": "<|code|>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"special": false
|
| 118 |
+
},
|
| 119 |
+
"14": {
|
| 120 |
+
"content": "<|file|>",
|
| 121 |
+
"lstrip": false,
|
| 122 |
+
"normalized": false,
|
| 123 |
+
"rstrip": false,
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"special": false
|
| 126 |
+
},
|
| 127 |
+
"102397": {
|
| 128 |
+
"content": "<|prefix|>",
|
| 129 |
+
"lstrip": false,
|
| 130 |
+
"normalized": false,
|
| 131 |
+
"rstrip": false,
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"special": false
|
| 134 |
+
},
|
| 135 |
+
"102398": {
|
| 136 |
+
"content": "<|suffix|>",
|
| 137 |
+
"lstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"rstrip": false,
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"special": false
|
| 142 |
+
},
|
| 143 |
+
"102399": {
|
| 144 |
+
"content": "<|middle|>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"special": false
|
| 150 |
+
}
|
| 151 |
+
},
|
| 152 |
+
"bos_token": "<s>",
|
| 153 |
+
"clean_up_tokenization_spaces": false,
|
| 154 |
+
"cls_token": "<cls>",
|
| 155 |
+
"do_lower_case": false,
|
| 156 |
+
"eos_token": "</s>",
|
| 157 |
+
"extra_ids": 0,
|
| 158 |
+
"extra_special_tokens": {},
|
| 159 |
+
"keep_accents": true,
|
| 160 |
+
"legacy": false,
|
| 161 |
+
"mask_token": "<mask>",
|
| 162 |
+
"model_max_length": 8192,
|
| 163 |
+
"pad_token": "<pad>",
|
| 164 |
+
"padding_side": "right",
|
| 165 |
+
"sep_token": "<sep>",
|
| 166 |
+
"sp_model_kwargs": {},
|
| 167 |
+
"spaces_between_special_tokens": false,
|
| 168 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 169 |
+
"unk_token": "<unk>",
|
| 170 |
+
"use_default_system_prompt": false
|
| 171 |
+
}
|
checkpoint-285000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-285000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9160177d49df3f031ebcb090af2b1e306d3679081035ca8245b2ac268971306c
|
| 3 |
+
size 5304
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 147501544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85be6777e1bdcafd4ef6a3faf62dcaf0904d018014734d348a8665b630303b3d
|
| 3 |
size 147501544
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 8192,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 8192
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 3,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9160177d49df3f031ebcb090af2b1e306d3679081035ca8245b2ac268971306c
|
| 3 |
size 5304
|