初始化项目，由ModelHub XC社区提供模型
Model: zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
75
README.md
Normal file
75
README.md
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen3-0.6B-Base
|
||||||
|
library_name: transformers
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- qwen3
|
||||||
|
- math
|
||||||
|
- sft
|
||||||
|
- qlora
|
||||||
|
- merged-lora
|
||||||
|
- fp16
|
||||||
|
---
|
||||||
|
|
||||||
|
# qwen3-0.6b-math-l45-qlora-merged-fp16-v2
|
||||||
|
|
||||||
|
Merged fp16 model from `Qwen/Qwen3-0.6B-Base` plus a QLoRA SFT adapter trained for MATH level 4-5 problem solving.
|
||||||
|
|
||||||
|
This is the corrected SFT v2 run using the train split for training. Final 500-question evaluation is intentionally separate.
|
||||||
|
|
||||||
|
## Training Summary
|
||||||
|
|
||||||
|
- Base model: `Qwen/Qwen3-0.6B-Base`
|
||||||
|
- Train file: `/kaggle/input/datasets/anurhalizah/math-he/math_level45_train.parquet`
|
||||||
|
- Test file: `/kaggle/input/datasets/anurhalizah/math-he/math_level45_test.parquet`
|
||||||
|
- Train rows used: `3994`
|
||||||
|
- Train subset size: `3994`
|
||||||
|
- Smoke loss eval rows: `200`
|
||||||
|
- Max sequence length: `2048`
|
||||||
|
- Epochs: `3`
|
||||||
|
- Learning rate: `0.0002`
|
||||||
|
- Precision: fp16
|
||||||
|
- Merge method: `manual_lora_cpu`
|
||||||
|
- Merged LoRA matrices: `196`
|
||||||
|
|
||||||
|
## Prompt Format
|
||||||
|
|
||||||
|
```text
|
||||||
|
### System:
|
||||||
|
{system_prompt}
|
||||||
|
|
||||||
|
### Problem:
|
||||||
|
{problem}
|
||||||
|
|
||||||
|
### Solution:
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
System prompt:
|
||||||
|
|
||||||
|
```text
|
||||||
|
You are a precise mathematical problem solver.
|
||||||
|
Follow this exact output contract:
|
||||||
|
1. Solve the problem step by step with concise reasoning.
|
||||||
|
2. Use valid LaTeX math notation for mathematical expressions.
|
||||||
|
3. Preserve LaTeX commands such as \frac{...}{...}, \sqrt{...}, x^{...}, subscripts, equations, and inequalities.
|
||||||
|
4. Put the final answer on its own last line exactly in this form: Final Answer: \boxed{...}
|
||||||
|
5. Do not use Markdown code fences.
|
||||||
|
6. Do not switch to a different answer format.
|
||||||
|
```
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import torch
|
||||||
|
|
||||||
|
repo_id = "zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2"
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
repo_id,
|
||||||
|
torch_dtype=torch.float16,
|
||||||
|
device_map="auto",
|
||||||
|
trust_remote_code=True,
|
||||||
|
)
|
||||||
|
```
|
||||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# 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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in message.content %}
|
||||||
|
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "float16",
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1024,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3072,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": null,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.8.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": false,
|
||||||
|
"eos_token_id": 151643,
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"transformers_version": "5.8.1"
|
||||||
|
}
|
||||||
16
merge_info.json
Normal file
16
merge_info.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"model_id": "Qwen/Qwen3-0.6B-Base",
|
||||||
|
"run_name": "qwen3-0.6b-math-l45-qlora-sft-v2",
|
||||||
|
"hf_repo_id": "zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2",
|
||||||
|
"adapter_dir": "/kaggle/working/qwen3-0.6b-math-l45-qlora-sft-v2/adapter",
|
||||||
|
"merged_dir": "/kaggle/working/qwen3-0.6b-math-l45-qlora-sft-v2/merged-fp16",
|
||||||
|
"merge_method": "manual_lora_cpu",
|
||||||
|
"merged_matrix_count": 196,
|
||||||
|
"unique_target_module_count": 196,
|
||||||
|
"elapsed_seconds": 0.4837789409994002,
|
||||||
|
"source_adapter_dir": "/kaggle/working/qwen3-0.6b-math-l45-qlora-sft-v2/adapter",
|
||||||
|
"lora_alpha": 32.0,
|
||||||
|
"r": 16,
|
||||||
|
"use_rslora": false,
|
||||||
|
"fan_in_fan_out": false
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b33a1d7eeb033899a368acb8815db189243b159b56dac78e641e0f416545e756
|
||||||
|
size 1192134784
|
||||||
8
prompt_config.json
Normal file
8
prompt_config.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"model_id": "Qwen/Qwen3-0.6B-Base",
|
||||||
|
"prompt_template": "### System:\n{system_prompt}\n\n### Problem:\n{problem}\n\n### Solution:\n",
|
||||||
|
"system_prompt": "You are a precise mathematical problem solver.\nFollow this exact output contract:\n1. Solve the problem step by step with concise reasoning.\n2. Use valid LaTeX math notation for mathematical expressions.\n3. Preserve LaTeX commands such as \\frac{...}{...}, \\sqrt{...}, x^{...}, subscripts, equations, and inequalities.\n4. Put the final answer on its own last line exactly in this form: Final Answer: \\boxed{...}\n5. Do not use Markdown code fences.\n6. Do not switch to a different answer format.",
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"add_final_answer_line_from_last_boxed": true
|
||||||
|
}
|
||||||
24
run_config.json
Normal file
24
run_config.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"model_id": "Qwen/Qwen3-0.6B-Base",
|
||||||
|
"run_name": "qwen3-0.6b-math-l45-qlora-sft-v2",
|
||||||
|
"hf_repo_id": "zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2",
|
||||||
|
"train_file": "/kaggle/input/datasets/anurhalizah/math-he/math_level45_train.parquet",
|
||||||
|
"test_file": "/kaggle/input/datasets/anurhalizah/math-he/math_level45_test.parquet",
|
||||||
|
"train_subset_size": 3994,
|
||||||
|
"train_rows_used": 3994,
|
||||||
|
"loss_eval_rows_used": 200,
|
||||||
|
"max_seq_length": 2048,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"learning_rate": 0.0002,
|
||||||
|
"per_device_train_batch_size": 1,
|
||||||
|
"per_device_eval_batch_size": 1,
|
||||||
|
"gradient_accumulation_steps": 8,
|
||||||
|
"fp16": true,
|
||||||
|
"bf16": false,
|
||||||
|
"qlora": true,
|
||||||
|
"shuffle_train": true,
|
||||||
|
"world_size": 1,
|
||||||
|
"device_map": "balanced",
|
||||||
|
"max_memory": "{0: 13958643712, 1: 13958643712}",
|
||||||
|
"final_eval_note": "Final 500-question evaluation is intentionally separate."
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"is_local": true,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user