Training in progress, step 100
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- chat_template.jinja +1 -14
- tokenizer.json +2 -2
- tokenizer_config.json +14 -62
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-
|
5 |
"bias": "none",
|
6 |
"corda_config": null,
|
7 |
"eva_config": null,
|
@@ -24,8 +24,8 @@
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
-
"
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"trainable_token_indices": null,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
5 |
"bias": "none",
|
6 |
"corda_config": null,
|
7 |
"eva_config": null,
|
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
+
"q_proj",
|
28 |
+
"v_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"trainable_token_indices": null,
|
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 sha256:1df3cb6bd90c96e6e4b15847c1e89f5bf305d6044d58e1ec0210426af14247c5
|
3 |
+
size 8731128
|
chat_template.jinja
CHANGED
@@ -1,14 +1 @@
|
|
1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt=''
|
2 |
-
|
3 |
-
' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<|User|>' + content + '<|Assistant|>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
|
4 |
-
' + '```json' + '
|
5 |
-
' + tool['function']['arguments'] + '
|
6 |
-
' + '```' + '<|tool▁call▁end|>'}}{%- else %}{{content + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
|
7 |
-
' + '```json' + '
|
8 |
-
' + tool['function']['arguments'] + '
|
9 |
-
' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
|
10 |
-
' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
|
11 |
-
' + '```json' + '
|
12 |
-
' + tool['function']['arguments'] + '
|
13 |
-
' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + content + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
|
14 |
-
<|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}
|
|
|
1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
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:e51761ae26bab0e3530dd15e9eccf5b959916140e2fe264d45ccc944fa4040c8
|
3 |
+
size 11423071
|
tokenizer_config.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
-
"add_bos_token":
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"151643": {
|
7 |
-
"content": "<|
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
@@ -12,23 +12,23 @@
|
|
12 |
"special": true
|
13 |
},
|
14 |
"151644": {
|
15 |
-
"content": "
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
-
"special":
|
21 |
},
|
22 |
"151645": {
|
23 |
-
"content": "<|
|
24 |
"lstrip": false,
|
25 |
"normalized": false,
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
-
"special":
|
29 |
},
|
30 |
"151646": {
|
31 |
-
"content": "
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
@@ -36,28 +36,28 @@
|
|
36 |
"special": true
|
37 |
},
|
38 |
"151647": {
|
39 |
-
"content": "<|
|
40 |
"lstrip": false,
|
41 |
"normalized": false,
|
42 |
"rstrip": false,
|
43 |
"single_word": false,
|
44 |
-
"special":
|
45 |
},
|
46 |
"151648": {
|
47 |
-
"content": "
|
48 |
"lstrip": false,
|
49 |
"normalized": false,
|
50 |
"rstrip": false,
|
51 |
"single_word": false,
|
52 |
-
"special":
|
53 |
},
|
54 |
"151649": {
|
55 |
-
"content": "
|
56 |
"lstrip": false,
|
57 |
"normalized": false,
|
58 |
"rstrip": false,
|
59 |
"single_word": false,
|
60 |
-
"special":
|
61 |
},
|
62 |
"151650": {
|
63 |
"content": "<|quad_start|>",
|
@@ -178,54 +178,6 @@
|
|
178 |
"rstrip": false,
|
179 |
"single_word": false,
|
180 |
"special": false
|
181 |
-
},
|
182 |
-
"151665": {
|
183 |
-
"content": "<tool_response>",
|
184 |
-
"lstrip": false,
|
185 |
-
"normalized": false,
|
186 |
-
"rstrip": false,
|
187 |
-
"single_word": false,
|
188 |
-
"special": false
|
189 |
-
},
|
190 |
-
"151666": {
|
191 |
-
"content": "</tool_response>",
|
192 |
-
"lstrip": false,
|
193 |
-
"normalized": false,
|
194 |
-
"rstrip": false,
|
195 |
-
"single_word": false,
|
196 |
-
"special": false
|
197 |
-
},
|
198 |
-
"151667": {
|
199 |
-
"content": "<think>",
|
200 |
-
"lstrip": false,
|
201 |
-
"normalized": false,
|
202 |
-
"rstrip": false,
|
203 |
-
"single_word": false,
|
204 |
-
"special": false
|
205 |
-
},
|
206 |
-
"151668": {
|
207 |
-
"content": "</think>",
|
208 |
-
"lstrip": false,
|
209 |
-
"normalized": false,
|
210 |
-
"rstrip": false,
|
211 |
-
"single_word": false,
|
212 |
-
"special": false
|
213 |
-
},
|
214 |
-
"151669": {
|
215 |
-
"content": "<|User|>",
|
216 |
-
"lstrip": false,
|
217 |
-
"normalized": false,
|
218 |
-
"rstrip": false,
|
219 |
-
"single_word": false,
|
220 |
-
"special": false
|
221 |
-
},
|
222 |
-
"151670": {
|
223 |
-
"content": "<|Assistant|>",
|
224 |
-
"lstrip": false,
|
225 |
-
"normalized": false,
|
226 |
-
"rstrip": false,
|
227 |
-
"single_word": false,
|
228 |
-
"special": false
|
229 |
}
|
230 |
},
|
231 |
"bos_token": "<|begin▁of▁sentence|>",
|
@@ -233,7 +185,7 @@
|
|
233 |
"eos_token": "<|end▁of▁sentence|>",
|
234 |
"extra_special_tokens": {},
|
235 |
"legacy": true,
|
236 |
-
"model_max_length":
|
237 |
"pad_token": "<|end▁of▁sentence|>",
|
238 |
"sp_model_kwargs": {},
|
239 |
"tokenizer_class": "LlamaTokenizerFast",
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"151643": {
|
7 |
+
"content": "<|end▁of▁sentence|>",
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
|
|
12 |
"special": true
|
13 |
},
|
14 |
"151644": {
|
15 |
+
"content": "<|User|>",
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
+
"special": false
|
21 |
},
|
22 |
"151645": {
|
23 |
+
"content": "<|Assistant|>",
|
24 |
"lstrip": false,
|
25 |
"normalized": false,
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
+
"special": false
|
29 |
},
|
30 |
"151646": {
|
31 |
+
"content": "<|begin▁of▁sentence|>",
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
34 |
"rstrip": false,
|
|
|
36 |
"special": true
|
37 |
},
|
38 |
"151647": {
|
39 |
+
"content": "<|EOT|>",
|
40 |
"lstrip": false,
|
41 |
"normalized": false,
|
42 |
"rstrip": false,
|
43 |
"single_word": false,
|
44 |
+
"special": false
|
45 |
},
|
46 |
"151648": {
|
47 |
+
"content": "<think>",
|
48 |
"lstrip": false,
|
49 |
"normalized": false,
|
50 |
"rstrip": false,
|
51 |
"single_word": false,
|
52 |
+
"special": false
|
53 |
},
|
54 |
"151649": {
|
55 |
+
"content": "</think>",
|
56 |
"lstrip": false,
|
57 |
"normalized": false,
|
58 |
"rstrip": false,
|
59 |
"single_word": false,
|
60 |
+
"special": false
|
61 |
},
|
62 |
"151650": {
|
63 |
"content": "<|quad_start|>",
|
|
|
178 |
"rstrip": false,
|
179 |
"single_word": false,
|
180 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
}
|
182 |
},
|
183 |
"bos_token": "<|begin▁of▁sentence|>",
|
|
|
185 |
"eos_token": "<|end▁of▁sentence|>",
|
186 |
"extra_special_tokens": {},
|
187 |
"legacy": true,
|
188 |
+
"model_max_length": 16384,
|
189 |
"pad_token": "<|end▁of▁sentence|>",
|
190 |
"sp_model_kwargs": {},
|
191 |
"tokenizer_class": "LlamaTokenizerFast",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5777
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36d320f4ecd5f44d7b3a86fb3f73f4c175f658ad931311d7cdf1a170127a01f1
|
3 |
size 5777
|