Upload folder using huggingface_hub
Browse files- added_tokens.json +4 -0
- config.json +32 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +187 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|end_of_turn|>": 102401,
|
3 |
+
"<|start_of_turn|>": 102400
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sbintuitions/sarashina2.1-1b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 112,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 1792,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 6272,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"pad_token_id": 3,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 500000,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.46.3",
|
29 |
+
"unsloth_version": "2024.12.8",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 102402
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 8192,
|
6 |
+
"pad_token_id": 3,
|
7 |
+
"transformers_version": "4.46.3"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c58976b502792127695bd0ffc1d164a730a91adbfc49daa7a4af6c9dc5f4e27
|
3 |
+
size 2815117504
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2aaa9d63074b75e27ef4e54bfa37f7a6ae7f6fba877724cdc31576ed5f3640ca
|
3 |
+
size 2486357050
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6246754fb8f452326ac23bbc1d9ccf2ab04d37a4184e397bc00a914c5ad489c4
|
3 |
+
size 1064
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
|
3 |
+
size 1831879
|
tokenizer_config.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_dummy_prefix_space": false,
|
4 |
+
"add_eos_token": false,
|
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": true,
|
75 |
+
"rstrip": false,
|
76 |
+
"single_word": false,
|
77 |
+
"special": false
|
78 |
+
},
|
79 |
+
"9": {
|
80 |
+
"content": "<|user|>",
|
81 |
+
"lstrip": false,
|
82 |
+
"normalized": true,
|
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 |
+
"102400": {
|
152 |
+
"content": "<|start_of_turn|>",
|
153 |
+
"lstrip": false,
|
154 |
+
"normalized": true,
|
155 |
+
"rstrip": false,
|
156 |
+
"single_word": false,
|
157 |
+
"special": false
|
158 |
+
},
|
159 |
+
"102401": {
|
160 |
+
"content": "<|end_of_turn|>",
|
161 |
+
"lstrip": false,
|
162 |
+
"normalized": true,
|
163 |
+
"rstrip": false,
|
164 |
+
"single_word": false,
|
165 |
+
"special": false
|
166 |
+
}
|
167 |
+
},
|
168 |
+
"bos_token": "<s>",
|
169 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] != 'assistant' and message['role'] != 'user') %}{{ raise_exception('Only user and assistant role are supported') }}{% endif %}{{ '<|start_of_turn|>' + '<|' + message['role'] + '|>'+ '\\n' + message['content'] | trim + '<|end_of_turn|>\\n' }}{% endfor %}{% if add_generation_prompt %}{{'<|start_of_turn|><|assistant|>\\n'}}{% endif %}\n",
|
170 |
+
"clean_up_tokenization_spaces": false,
|
171 |
+
"cls_token": "<cls>",
|
172 |
+
"do_lower_case": false,
|
173 |
+
"eos_token": "</s>",
|
174 |
+
"extra_ids": 0,
|
175 |
+
"keep_accents": true,
|
176 |
+
"legacy": false,
|
177 |
+
"mask_token": "<mask>",
|
178 |
+
"model_max_length": 8192,
|
179 |
+
"pad_token": "<pad>",
|
180 |
+
"padding_side": "right",
|
181 |
+
"sep_token": "<sep>",
|
182 |
+
"sp_model_kwargs": {},
|
183 |
+
"spaces_between_special_tokens": false,
|
184 |
+
"tokenizer_class": "LlamaTokenizer",
|
185 |
+
"unk_token": "<unk>",
|
186 |
+
"use_default_system_prompt": false
|
187 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ce5812648d78cd5f958e3589449d35a9faacc8d12120d4cf34b8aada39d3ce2
|
3 |
+
size 5496
|