Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +23 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-10000/model.safetensors +3 -0
- checkpoint-100000/trainer_state.json +3 -0
- checkpoint-11000/config.json +33 -0
- checkpoint-11000/generation_config.json +6 -0
- checkpoint-11000/special_tokens_map.json +16 -0
- checkpoint-11000/tokenizer.json +0 -0
- checkpoint-11000/tokenizer_config.json +240 -0
- checkpoint-11000/trainer_state.json +0 -0
- checkpoint-11000/training_args.bin +3 -0
- checkpoint-14000/model.safetensors +3 -0
- checkpoint-15000/config.json +33 -0
- checkpoint-15000/generation_config.json +6 -0
- checkpoint-15000/special_tokens_map.json +16 -0
- checkpoint-15000/tokenizer.json +0 -0
- checkpoint-15000/tokenizer_config.json +240 -0
- checkpoint-15000/trainer_state.json +0 -0
- checkpoint-15000/training_args.bin +3 -0
- checkpoint-16000/model.safetensors +3 -0
- checkpoint-17000/model.safetensors +3 -0
- checkpoint-20000/training_args.bin +3 -0
- checkpoint-21000/model.safetensors +3 -0
- checkpoint-22000/model.safetensors +3 -0
- checkpoint-25000/model.safetensors +3 -0
- checkpoint-25000/training_args.bin +3 -0
- checkpoint-26000/model.safetensors +3 -0
- checkpoint-27000/model.safetensors +3 -0
- checkpoint-28000/model.safetensors +3 -0
- checkpoint-29000/model.safetensors +3 -0
- checkpoint-30000/model.safetensors +3 -0
- checkpoint-30000/training_args.bin +3 -0
- checkpoint-31000/model.safetensors +3 -0
- checkpoint-32000/model.safetensors +3 -0
- checkpoint-33000/model.safetensors +3 -0
- checkpoint-34000/model.safetensors +3 -0
- checkpoint-35000/model.safetensors +3 -0
- checkpoint-35000/training_args.bin +3 -0
- checkpoint-38000/model.safetensors +3 -0
- checkpoint-39000/model.safetensors +3 -0
- checkpoint-41000/model.safetensors +3 -0
- checkpoint-43000/model.safetensors +3 -0
- checkpoint-44000/model.safetensors +3 -0
- checkpoint-45000/model.safetensors +3 -0
- checkpoint-46000/model.safetensors +3 -0
- checkpoint-48000/model.safetensors +3 -0
- checkpoint-50000/model.safetensors +3 -0
- checkpoint-50000/training_args.bin +3 -0
- checkpoint-52000/config.json +33 -0
- checkpoint-52000/generation_config.json +6 -0
.gitattributes
CHANGED
@@ -39,3 +39,26 @@ checkpoint-99000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
|
39 |
checkpoint-94000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
40 |
checkpoint-85000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
41 |
checkpoint-87000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
checkpoint-94000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
40 |
checkpoint-85000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
41 |
checkpoint-87000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
42 |
+
checkpoint-84000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
43 |
+
checkpoint-73000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
44 |
+
checkpoint-97000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
45 |
+
checkpoint-79000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
46 |
+
checkpoint-74000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
47 |
+
checkpoint-83000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
48 |
+
checkpoint-76000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
49 |
+
checkpoint-89000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
50 |
+
checkpoint-93000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
51 |
+
checkpoint-88000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
52 |
+
checkpoint-100000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
53 |
+
checkpoint-86000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
54 |
+
checkpoint-98000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
55 |
+
checkpoint-72000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
56 |
+
checkpoint-90000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
57 |
+
checkpoint-82000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
58 |
+
checkpoint-78000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
59 |
+
checkpoint-81000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
60 |
+
checkpoint-92000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
61 |
+
checkpoint-91000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
62 |
+
checkpoint-77000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
63 |
+
checkpoint-96000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
64 |
+
checkpoint-95000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-10000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20bcd790dab74ba0af68bfe3f4ba68a0fd0ac77ffe3140b743535a0d8a01d0f1
|
3 |
+
size 57791008
|
checkpoint-100000/trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7304a36eed7a4322e86bab45304dba1b0ac67271ea3be4367d83ce612631cde6
|
3 |
+
size 14919597
|
checkpoint-11000/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JW17/SmolLM-14m-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"flash_attn": true,
|
11 |
+
"head_dim": 32,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 128,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 512,
|
16 |
+
"is_llama_config": true,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"mlp_bias": false,
|
19 |
+
"model_type": "llama",
|
20 |
+
"num_attention_heads": 4,
|
21 |
+
"num_hidden_layers": 6,
|
22 |
+
"num_key_value_heads": 4,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_interleaved": false,
|
26 |
+
"rope_scaling": null,
|
27 |
+
"rope_theta": 100000,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.48.1",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50280
|
33 |
+
}
|
checkpoint-11000/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.48.1"
|
6 |
+
}
|
checkpoint-11000/special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<|padding|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
checkpoint-11000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11000/tokenizer_config.json
ADDED
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "|||IP_ADDRESS|||",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": false
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50277": {
|
207 |
+
"content": "|||EMAIL_ADDRESS|||",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": true,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"50278": {
|
215 |
+
"content": "|||PHONE_NUMBER|||",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": true,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"50279": {
|
223 |
+
"content": "<|endoftext|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
}
|
230 |
+
},
|
231 |
+
"bos_token": null,
|
232 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
233 |
+
"clean_up_tokenization_spaces": true,
|
234 |
+
"eos_token": "<|endoftext|>",
|
235 |
+
"extra_special_tokens": {},
|
236 |
+
"model_max_length": 1000000000000000019884624838656,
|
237 |
+
"pad_token": "<|padding|>",
|
238 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
239 |
+
"unk_token": null
|
240 |
+
}
|
checkpoint-11000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-11000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-14000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d51a162f642cfcdb8d324a7701269730330216bc111349518d2c8829764d1e2c
|
3 |
+
size 57791008
|
checkpoint-15000/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JW17/SmolLM-14m-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"flash_attn": true,
|
11 |
+
"head_dim": 32,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 128,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 512,
|
16 |
+
"is_llama_config": true,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"mlp_bias": false,
|
19 |
+
"model_type": "llama",
|
20 |
+
"num_attention_heads": 4,
|
21 |
+
"num_hidden_layers": 6,
|
22 |
+
"num_key_value_heads": 4,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_interleaved": false,
|
26 |
+
"rope_scaling": null,
|
27 |
+
"rope_theta": 100000,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.48.1",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50280
|
33 |
+
}
|
checkpoint-15000/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.48.1"
|
6 |
+
}
|
checkpoint-15000/special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<|padding|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
checkpoint-15000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/tokenizer_config.json
ADDED
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "|||IP_ADDRESS|||",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": false
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50277": {
|
207 |
+
"content": "|||EMAIL_ADDRESS|||",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": true,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"50278": {
|
215 |
+
"content": "|||PHONE_NUMBER|||",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": true,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"50279": {
|
223 |
+
"content": "<|endoftext|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
}
|
230 |
+
},
|
231 |
+
"bos_token": null,
|
232 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
233 |
+
"clean_up_tokenization_spaces": true,
|
234 |
+
"eos_token": "<|endoftext|>",
|
235 |
+
"extra_special_tokens": {},
|
236 |
+
"model_max_length": 1000000000000000019884624838656,
|
237 |
+
"pad_token": "<|padding|>",
|
238 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
239 |
+
"unk_token": null
|
240 |
+
}
|
checkpoint-15000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-15000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-16000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00218322afd086f93ca2249f820f606c4537e3d40c1de98deb3f1e7fd97ce1bb
|
3 |
+
size 57791008
|
checkpoint-17000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236ac7d677ee0880fb243951059cced7b35b88c20153815670e7a5ad0d9a6983
|
3 |
+
size 57791008
|
checkpoint-20000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-21000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dc82d0aefba1729b6a67e4273b85d6afec56a2a3e57b80f7de2514262876820
|
3 |
+
size 57791008
|
checkpoint-22000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aed4ebf1809752f8b3e423d65dd7fea7f2171930dd708cf982f9aa8b24ed053
|
3 |
+
size 57791008
|
checkpoint-25000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c47b9bf31cea231dc91d88f79ec57de2aad6c9fe318ba64f70539f3531651a
|
3 |
+
size 57791008
|
checkpoint-25000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-26000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d1d466717dd11d49fabdc7bc768c11cc122dfe7cd5dd56679ac12932672b5f
|
3 |
+
size 57791008
|
checkpoint-27000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d19587c45bf7894cfce1bf0ab42e408cc44de580fe69cff382b9c3f128fab4
|
3 |
+
size 57791008
|
checkpoint-28000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40680c43b4171031784e83cc286e8374f2ceeb798efe779ae2309ad7f6f7fa9d
|
3 |
+
size 57791008
|
checkpoint-29000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ddc7b1ed099c0c156d52698deaa47b2f95fe7b29d2be40f14fbe9f70aeeeb0
|
3 |
+
size 57791008
|
checkpoint-30000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4964148b8a74ef242d37c73c76dfd36d33cb7a92614ffddffacd723cb937447b
|
3 |
+
size 57791008
|
checkpoint-30000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-31000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d8bc3c0eb967c9099da9a4c1b0d8196fcb1f1e03fa1685cedb0b7b9dd3cfd5
|
3 |
+
size 57791008
|
checkpoint-32000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df93f6c140255dca515604d78c1d1968aeec9ca56c003024351a2eed5cc1351
|
3 |
+
size 57791008
|
checkpoint-33000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2959eab33f264b7c74deae221814cb8e9d1afa27198accd0f1bc801728933d6
|
3 |
+
size 57791008
|
checkpoint-34000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dbcfa1c7743ba120b023e0f5d271031ccf4c9a1ac195a42ef4b8ee720a1b53c
|
3 |
+
size 57791008
|
checkpoint-35000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:573c046d18a580b611fb7462e76627ce66f25a13143283cce5fbeba9f8de0e65
|
3 |
+
size 57791008
|
checkpoint-35000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-38000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:692ad9ed05b5ce549ab4b86c4d4b539cea26c97117e54bcd83b84e3fd45dbec8
|
3 |
+
size 57791008
|
checkpoint-39000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec9b6a9c5e016b77d176454139ffcedc632832661afbcb2d959b947ed21a953e
|
3 |
+
size 57791008
|
checkpoint-41000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1d64e3c9fced5d1b4eaeeb6b00335f2e18e299a75ef35d534f129ac0d8c02d0
|
3 |
+
size 57791008
|
checkpoint-43000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53011c6196ae4257463fea4e0c38a49ff307912bc01bb91a7c5938403a3d80fa
|
3 |
+
size 57791008
|
checkpoint-44000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be0d1cd245c62f33d3d7bcaa3da7906d80f8b86a4c2d8d744df958155c73ba37
|
3 |
+
size 57791008
|
checkpoint-45000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a60cee81ca573e2221bc4840426b84197e84881abbc5db5faf9c04ef6868fa48
|
3 |
+
size 57791008
|
checkpoint-46000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11aa0e1f589e02b24341773474c81d945bfef25b84358102ff65dce2991267db
|
3 |
+
size 57791008
|
checkpoint-48000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bad0f28978ee9247df482efac376f0d3fc7418289717f45c373f7bb54841528
|
3 |
+
size 57791008
|
checkpoint-50000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80debfe102f928aaee371cebab34228c21a048f4d366fcef7b8bbc78c3472fb3
|
3 |
+
size 57791008
|
checkpoint-50000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16204b05d2a9d34e94fb9daf7e1142eb825aaf16c8c84d8db978053ba172d2c9
|
3 |
+
size 5368
|
checkpoint-52000/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JW17/SmolLM-14m-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"flash_attn": true,
|
11 |
+
"head_dim": 32,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 128,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 512,
|
16 |
+
"is_llama_config": true,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"mlp_bias": false,
|
19 |
+
"model_type": "llama",
|
20 |
+
"num_attention_heads": 4,
|
21 |
+
"num_hidden_layers": 6,
|
22 |
+
"num_key_value_heads": 4,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_interleaved": false,
|
26 |
+
"rope_scaling": null,
|
27 |
+
"rope_theta": 100000,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.48.1",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50280
|
33 |
+
}
|
checkpoint-52000/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.48.1"
|
6 |
+
}
|