update unsloth_qwen_2.5_32B_bnb_4bit_finetuned
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- tokenizer_config.json +2 -2
- trainer_state.json +0 -0
- training_args.bin +2 -2
adapter_config.json
CHANGED
@@ -10,8 +10,8 @@
|
|
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": null,
|
@@ -23,10 +23,10 @@
|
|
23 |
"v_proj",
|
24 |
"q_proj",
|
25 |
"gate_proj",
|
26 |
-
"up_proj",
|
27 |
-
"down_proj",
|
28 |
"k_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
|
|
23 |
"v_proj",
|
24 |
"q_proj",
|
25 |
"gate_proj",
|
|
|
|
|
26 |
"k_proj",
|
27 |
+
"down_proj",
|
28 |
+
"o_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 2147605960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe44b8852af1689550ee8485472499b4ed8da9855c91969e96ea7683cd845cf
|
3 |
size 2147605960
|
tokenizer_config.json
CHANGED
@@ -203,12 +203,12 @@
|
|
203 |
"<|video_pad|>"
|
204 |
],
|
205 |
"bos_token": null,
|
206 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{
|
207 |
"clean_up_tokenization_spaces": false,
|
208 |
"eos_token": "<|im_end|>",
|
209 |
"errors": "replace",
|
210 |
"model_max_length": 32768,
|
211 |
-
"pad_token": "<|
|
212 |
"padding_side": "right",
|
213 |
"split_special_tokens": false,
|
214 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
203 |
"<|video_pad|>"
|
204 |
],
|
205 |
"bos_token": null,
|
206 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
207 |
"clean_up_tokenization_spaces": false,
|
208 |
"eos_token": "<|im_end|>",
|
209 |
"errors": "replace",
|
210 |
"model_max_length": 32768,
|
211 |
+
"pad_token": "<|PAD_TOKEN|>",
|
212 |
"padding_side": "right",
|
213 |
"split_special_tokens": false,
|
214 |
"tokenizer_class": "Qwen2Tokenizer",
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
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 sha256:567bbbf652b8940e9b6f836c06b4f263b6a9c865e7ee91dad66f2e94a1d2ff0c
|
3 |
+
size 5560
|