Training in progress, epoch 1
Browse files- adapter_config.json +10 -10
- adapter_model.safetensors +2 -2
- config.json +18 -4
- special_tokens_map.json +6 -6
- tokenizer.json +25 -7
- tokenizer_config.json +21 -5
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -3,15 +3,15 @@
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
5 |
"bias": "none",
|
6 |
-
"fan_in_fan_out":
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
-
"lora_dropout": 0,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": [
|
@@ -19,17 +19,17 @@
|
|
19 |
"lm_head"
|
20 |
],
|
21 |
"peft_type": "LORA",
|
22 |
-
"r":
|
23 |
"rank_pattern": {},
|
24 |
-
"revision":
|
25 |
"target_modules": [
|
|
|
|
|
|
|
|
|
26 |
"down_proj",
|
27 |
"o_proj",
|
28 |
-
"
|
29 |
-
"q_proj",
|
30 |
-
"k_proj",
|
31 |
-
"up_proj",
|
32 |
-
"gate_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
5 |
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": [
|
|
|
19 |
"lm_head"
|
20 |
],
|
21 |
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"up_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj",
|
29 |
+
"gate_proj",
|
30 |
"down_proj",
|
31 |
"o_proj",
|
32 |
+
"k_proj"
|
|
|
|
|
|
|
|
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:588591505247958507363d98bfb2535733c13dde0ff41a2d5c05267a8ab37eb1
|
3 |
+
size 848358568
|
config.json
CHANGED
@@ -5,8 +5,8 @@
|
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
-
"bos_token_id":
|
9 |
-
"eos_token_id":
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
@@ -17,6 +17,21 @@
|
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 32,
|
19 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"rms_norm_eps": 1e-06,
|
21 |
"rope_scaling": {
|
22 |
"factor": 4.0,
|
@@ -26,7 +41,6 @@
|
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "bfloat16",
|
28 |
"transformers_version": "4.40.0.dev0",
|
29 |
-
"
|
30 |
-
"use_cache": true,
|
31 |
"vocab_size": 32256
|
32 |
}
|
|
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 32022,
|
9 |
+
"eos_token_id": 32023,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 32,
|
19 |
"pretraining_tp": 1,
|
20 |
+
"quantization_config": {
|
21 |
+
"_load_in_4bit": false,
|
22 |
+
"_load_in_8bit": true,
|
23 |
+
"bnb_4bit_compute_dtype": "float32",
|
24 |
+
"bnb_4bit_quant_storage": "uint8",
|
25 |
+
"bnb_4bit_quant_type": "fp4",
|
26 |
+
"bnb_4bit_use_double_quant": false,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": false,
|
32 |
+
"load_in_8bit": true,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
"rms_norm_eps": 1e-06,
|
36 |
"rope_scaling": {
|
37 |
"factor": 4.0,
|
|
|
41 |
"tie_word_embeddings": false,
|
42 |
"torch_dtype": "bfloat16",
|
43 |
"transformers_version": "4.40.0.dev0",
|
44 |
+
"use_cache": false,
|
|
|
45 |
"vocab_size": 32256
|
46 |
}
|
special_tokens_map.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
-
"normalized":
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
-
"normalized":
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
}
|
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
+
"content": "<|begin_of_sentence|>",
|
4 |
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|end_of_sentence|>",
|
11 |
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "<|end_of_sentence|>",
|
18 |
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
}
|
tokenizer.json
CHANGED
@@ -200,6 +200,24 @@
|
|
200 |
"rstrip": false,
|
201 |
"normalized": true,
|
202 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
203 |
}
|
204 |
],
|
205 |
"normalizer": {
|
@@ -258,7 +276,7 @@
|
|
258 |
"single": [
|
259 |
{
|
260 |
"SpecialToken": {
|
261 |
-
"id": "
|
262 |
"type_id": 0
|
263 |
}
|
264 |
},
|
@@ -272,7 +290,7 @@
|
|
272 |
"pair": [
|
273 |
{
|
274 |
"SpecialToken": {
|
275 |
-
"id": "
|
276 |
"type_id": 0
|
277 |
}
|
278 |
},
|
@@ -284,7 +302,7 @@
|
|
284 |
},
|
285 |
{
|
286 |
"SpecialToken": {
|
287 |
-
"id": "
|
288 |
"type_id": 1
|
289 |
}
|
290 |
},
|
@@ -296,13 +314,13 @@
|
|
296 |
}
|
297 |
],
|
298 |
"special_tokens": {
|
299 |
-
"
|
300 |
-
"id": "
|
301 |
"ids": [
|
302 |
-
|
303 |
],
|
304 |
"tokens": [
|
305 |
-
"
|
306 |
]
|
307 |
}
|
308 |
}
|
|
|
200 |
"rstrip": false,
|
201 |
"normalized": true,
|
202 |
"special": true
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"id": 32022,
|
206 |
+
"content": "<|begin_of_sentence|>",
|
207 |
+
"single_word": false,
|
208 |
+
"lstrip": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"normalized": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"id": 32023,
|
215 |
+
"content": "<|end_of_sentence|>",
|
216 |
+
"single_word": false,
|
217 |
+
"lstrip": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"normalized": false,
|
220 |
+
"special": true
|
221 |
}
|
222 |
],
|
223 |
"normalizer": {
|
|
|
276 |
"single": [
|
277 |
{
|
278 |
"SpecialToken": {
|
279 |
+
"id": "<|begin_of_sentence|>",
|
280 |
"type_id": 0
|
281 |
}
|
282 |
},
|
|
|
290 |
"pair": [
|
291 |
{
|
292 |
"SpecialToken": {
|
293 |
+
"id": "<|begin_of_sentence|>",
|
294 |
"type_id": 0
|
295 |
}
|
296 |
},
|
|
|
302 |
},
|
303 |
{
|
304 |
"SpecialToken": {
|
305 |
+
"id": "<|begin_of_sentence|>",
|
306 |
"type_id": 1
|
307 |
}
|
308 |
},
|
|
|
314 |
}
|
315 |
],
|
316 |
"special_tokens": {
|
317 |
+
"<|begin_of_sentence|>": {
|
318 |
+
"id": "<|begin_of_sentence|>",
|
319 |
"ids": [
|
320 |
+
32022
|
321 |
],
|
322 |
"tokens": [
|
323 |
+
"<|begin_of_sentence|>"
|
324 |
]
|
325 |
}
|
326 |
}
|
tokenizer_config.json
CHANGED
@@ -177,18 +177,34 @@
|
|
177 |
"rstrip": false,
|
178 |
"single_word": false,
|
179 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
}
|
181 |
},
|
182 |
-
"bos_token": "
|
183 |
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
184 |
"clean_up_tokenization_spaces": false,
|
185 |
-
"eos_token": "<|
|
186 |
"legacy": true,
|
187 |
"model_max_length": 16384,
|
188 |
-
"pad_token": "
|
189 |
-
"padding_side": "left",
|
190 |
"sp_model_kwargs": {},
|
191 |
"tokenizer_class": "LlamaTokenizer",
|
192 |
"unk_token": null,
|
193 |
-
"use_default_system_prompt": false
|
|
|
194 |
}
|
|
|
177 |
"rstrip": false,
|
178 |
"single_word": false,
|
179 |
"special": true
|
180 |
+
},
|
181 |
+
"32022": {
|
182 |
+
"content": "<|begin_of_sentence|>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"32023": {
|
190 |
+
"content": "<|end_of_sentence|>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
}
|
197 |
},
|
198 |
+
"bos_token": "<|begin_of_sentence|>",
|
199 |
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
200 |
"clean_up_tokenization_spaces": false,
|
201 |
+
"eos_token": "<|end_of_sentence|>",
|
202 |
"legacy": true,
|
203 |
"model_max_length": 16384,
|
204 |
+
"pad_token": "<|end_of_sentence|>",
|
|
|
205 |
"sp_model_kwargs": {},
|
206 |
"tokenizer_class": "LlamaTokenizer",
|
207 |
"unk_token": null,
|
208 |
+
"use_default_system_prompt": false,
|
209 |
+
"use_fast": true
|
210 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eaa08222fb80db93edb290a2d6190a3b510a1f8d4226cb8cefe6ee779fbded5
|
3 |
size 5880
|