Upload folder using huggingface_hub
Browse files- README.md +2 -2
- adapter_config.json +13 -11
- adapter_model.safetensors +2 -2
- special_tokens_map.json +7 -1
- tokenizer_config.json +5 -7
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
-
- PEFT 0.15.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/Qwen3-4B-unsloth-bnb-4bit
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.15.2
|
adapter_config.json
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
| 6 |
-
|
|
|
|
|
|
|
| 7 |
"fan_in_fan_out": false,
|
| 8 |
"inference_mode": true,
|
| 9 |
"init_lora_weights": true,
|
|
@@ -11,27 +13,27 @@
|
|
| 11 |
"layers_pattern": null,
|
| 12 |
"layers_to_transform": null,
|
| 13 |
"loftq_config": {},
|
| 14 |
-
"lora_alpha":
|
| 15 |
-
|
| 16 |
-
"lora_dropout": 0.
|
| 17 |
"megatron_config": null,
|
| 18 |
"megatron_core": "megatron.core",
|
| 19 |
"modules_to_save": null,
|
| 20 |
"peft_type": "LORA",
|
| 21 |
-
"r":
|
| 22 |
"rank_pattern": {},
|
| 23 |
"revision": null,
|
| 24 |
"target_modules": [
|
| 25 |
"k_proj",
|
| 26 |
-
"v_proj",
|
| 27 |
-
"down_proj",
|
| 28 |
"up_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
"gate_proj",
|
| 31 |
-
"
|
|
|
|
| 32 |
],
|
| 33 |
"task_type": "CAUSAL_LM",
|
| 34 |
-
|
| 35 |
"use_dora": false,
|
| 36 |
"use_rslora": false
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Qwen3-4B-unsloth-bnb-4bit",
|
| 5 |
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": true,
|
|
|
|
| 13 |
"layers_pattern": null,
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.2,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
"k_proj",
|
|
|
|
|
|
|
| 28 |
"up_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
"gate_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
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:a1770ca9a108f67908920a0c4fef8152a1570a413c2b839e8c5f39ea2c279295
|
| 3 |
+
size 528551264
|
special_tokens_map.json
CHANGED
|
@@ -21,5 +21,11 @@
|
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
|
|
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
}
|
tokenizer_config.json
CHANGED
|
@@ -227,17 +227,15 @@
|
|
| 227 |
"<|video_pad|>"
|
| 228 |
],
|
| 229 |
"bos_token": null,
|
| 230 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for
|
| 231 |
"clean_up_tokenization_spaces": false,
|
| 232 |
"eos_token": "<|im_end|>",
|
| 233 |
"errors": "replace",
|
| 234 |
"extra_special_tokens": {},
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"padding_side": "left",
|
| 239 |
"split_special_tokens": false,
|
| 240 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 241 |
-
"unk_token": null
|
| 242 |
-
"use_default_system_prompt": false
|
| 243 |
}
|
|
|
|
| 227 |
"<|video_pad|>"
|
| 228 |
],
|
| 229 |
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- set message = messages[index] %}\n {%- set tool_start = '<tool_response>' %}\n {%- set tool_start_length = tool_start|length %}\n {%- set start_of_message = message.content[:tool_start_length] %}\n {%- set tool_end = '</tool_response>' %}\n {%- set tool_end_length = tool_end|length %}\n {%- set start_pos = (message.content|length) - tool_end_length %}\n {%- if start_pos < 0 %}\n {%- set start_pos = 0 %}\n {%- endif %}\n {%- set end_of_message = message.content[start_pos:] %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = (message.content.split('</think>')|last).lstrip('\\n') %}\n {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\\n') %}\n {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
"clean_up_tokenization_spaces": false,
|
| 232 |
"eos_token": "<|im_end|>",
|
| 233 |
"errors": "replace",
|
| 234 |
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 40960,
|
| 236 |
+
"pad_token": "<|vision_pad|>",
|
| 237 |
+
"padding_side": "right",
|
|
|
|
| 238 |
"split_special_tokens": false,
|
| 239 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
|
|
|
| 241 |
}
|