Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Paper โข 2503.16252 โข Published โข 32
How to use from
OpenClawConfigure OpenClaw
# Install OpenClaw:
npm install -g openclaw@latest# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
--auth-choice custom-api-key \
--custom-base-url http://127.0.0.1:8080/v1 \
--custom-model-id "Mungert/Fin-R1-GGUF:" \
--custom-provider-id llama-cpp \
--custom-compatibility openai \
--custom-text-input \
--accept-risk \
--skip-healthRun OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"Quick Links
Fin-R1 GGUF Models
Choosing the Right Model Format
Selecting the correct model format depends on your hardware capabilities and memory constraints.
BF16 (Brain Float 16) โ Use if BF16 acceleration is available
- A 16-bit floating-point format designed for faster computation while retaining good precision.
- Provides similar dynamic range as FP32 but with lower memory usage.
- Recommended if your hardware supports BF16 acceleration (check your deviceโs specs).
- Ideal for high-performance inference with reduced memory footprint compared to FP32.
๐ Use BF16 if:
โ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
โ You want higher precision while saving memory.
โ You plan to requantize the model into another format.
๐ Avoid BF16 if:
โ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
โ You need compatibility with older devices that lack BF16 optimization.
F16 (Float 16) โ More widely supported than BF16
- A 16-bit floating-point high precision but with less of range of values than BF16.
- Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
- Slightly lower numerical precision than BF16 but generally sufficient for inference.
๐ Use F16 if:
โ Your hardware supports FP16 but not BF16.
โ You need a balance between speed, memory usage, and accuracy.
โ You are running on a GPU or another device optimized for FP16 computations.
๐ Avoid F16 if:
โ Your device lacks native FP16 support (it may run slower than expected).
โ You have memory limitations.
Quantized Models (Q4_K, Q6_K, Q8, etc.) โ For CPU & Low-VRAM Inference
Quantization reduces model size and memory usage while maintaining as much accuracy as possible.
- Lower-bit models (Q4_K) โ Best for minimal memory usage, may have lower precision.
- Higher-bit models (Q6_K, Q8_0) โ Better accuracy, requires more memory.
๐ Use Quantized Models if:
โ You are running inference on a CPU and need an optimized model.
โ Your device has low VRAM and cannot load full-precision models.
โ You want to reduce memory footprint while keeping reasonable accuracy.
๐ Avoid Quantized Models if:
โ You need maximum accuracy (full-precision models are better for this).
โ Your hardware has enough VRAM for higher-precision formats (BF16/F16).
Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)
These models are optimized for extreme memory efficiency, making them ideal for low-power devices or large-scale deployments where memory is a critical constraint.
IQ3_XS: Ultra-low-bit quantization (3-bit) with extreme memory efficiency.
- Use case: Best for ultra-low-memory devices where even Q4_K is too large.
- Trade-off: Lower accuracy compared to higher-bit quantizations.
IQ3_S: Small block size for maximum memory efficiency.
- Use case: Best for low-memory devices where IQ3_XS is too aggressive.
IQ3_M: Medium block size for better accuracy than IQ3_S.
- Use case: Suitable for low-memory devices where IQ3_S is too limiting.
Q4_K: 4-bit quantization with block-wise optimization for better accuracy.
- Use case: Best for low-memory devices where Q6_K is too large.
Q4_0: Pure 4-bit quantization, optimized for ARM devices.
- Use case: Best for ARM-based devices or low-memory environments.
Summary Table: Model Format Selection
| Model Format | Precision | Memory Usage | Device Requirements | Best Use Case |
|---|---|---|---|---|
| BF16 | Highest | High | BF16-supported GPU/CPUs | High-speed inference with reduced memory |
| F16 | High | High | FP16-supported devices | GPU inference when BF16 isnโt available |
| Q4_K | Medium Low | Low | CPU or Low-VRAM devices | Best for memory-constrained environments |
| Q6_K | Medium | Moderate | CPU with more memory | Better accuracy while still being quantized |
| Q8_0 | High | Moderate | CPU or GPU with enough VRAM | Best accuracy among quantized models |
| IQ3_XS | Very Low | Very Low | Ultra-low-memory devices | Extreme memory efficiency and low accuracy |
| Q4_0 | Low | Low | ARM or low-memory devices | llama.cpp can optimize for ARM devices |
Included Files & Details
Fin-R1-bf16.gguf
- Model weights preserved in BF16.
- Use this if you want to requantize the model into a different format.
- Best if your device supports BF16 acceleration.
Fin-R1-f16.gguf
- Model weights stored in F16.
- Use if your device supports FP16, especially if BF16 is not available.
Fin-R1-bf16-q8_0.gguf
- Output & embeddings remain in BF16.
- All other layers quantized to Q8_0.
- Use if your device supports BF16 and you want a quantized version.
Fin-R1-f16-q8_0.gguf
- Output & embeddings remain in F16.
- All other layers quantized to Q8_0.
Fin-R1-q4_k.gguf
- Output & embeddings quantized to Q8_0.
- All other layers quantized to Q4_K.
- Good for CPU inference with limited memory.
Fin-R1-q4_k_s.gguf
- Smallest Q4_K variant, using less memory at the cost of accuracy.
- Best for very low-memory setups.
Fin-R1-q6_k.gguf
- Output & embeddings quantized to Q8_0.
- All other layers quantized to Q6_K .
Fin-R1-q8_0.gguf
- Fully Q8 quantized model for better accuracy.
- Requires more memory but offers higher precision.
Fin-R1-iq3_xs.gguf
- IQ3_XS quantization, optimized for extreme memory efficiency.
- Best for ultra-low-memory devices.
Fin-R1-iq3_m.gguf
- IQ3_M quantization, offering a medium block size for better accuracy.
- Suitable for low-memory devices.
Fin-R1-q4_0.gguf
- Pure Q4_0 quantization, optimized for ARM devices.
- Best for low-memory environments.
- Prefer IQ4_NL for better accuracy.
๐ If you find these models useful
Please click like โค . Also Iโd really appreciate it if you could test my Network Monitor Assistant at ๐ Network Monitor Assitant.
๐ฌ Click the chat icon (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.
What I'm Testing
I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function".
๐ก TestLLM โ Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a timeโstill working on scaling!). If you're curious, I'd be happy to share how it works! .
The other Available AI Assistants
๐ข TurboLLM โ Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can Login or Download the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .
๐ต HugLLM โ Runs open-source Hugging Face models Fast, Runs small models (โ8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)
Final Word
I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAIโall out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is open source. Feel free to use whatever you find helpful.
If you appreciate the work, please consider buying me a coffee โ. Your support helps cover service costs and allows me to raise token limits for everyone.
I'm also open to job opportunities or sponsorship.
Thank you! ๐
Fin-R1 ๆฏไธๆฌพ้ๅฏน้่้ขๅๅคๆๆจ็็ๅคงๅ่ฏญ่จๆจกๅ๏ผ็ฑไธๆตท่ดข็ปๅคงๅญฆ็ป่ฎกไธๆฐๆฎ็งๅญฆๅญฆ้ขๅผ ็ซๆๆๆไธๅ ถ้ข่ก็้่ๅคง่ฏญ่จๆจกๅ่ฏพ้ข็ป๏ผSUFE-AIFLM-Lab๏ผ่ๅ่ดข่ทๆ่พฐ็ ๅๅนถๅผๆบๅๅธใ่ฏฅๆจกๅไปฅ Qwen2.5-7B-Instruct ไธบๅบๅบง๏ผ้่ฟ้ซ่ดจ้็ๅฏ้ช่ฏ้่้ฎ้ขๅพฎ่ฐ่ฎญ็ป๏ผๆ็ป่กจ็ฐๅจๅคไธช้่้ขๅๅบๅๆต่ฏไธ็่กจ็ฐ่พพๅฐๅ่ฏๆจกๅ็SOTAๆฐดๅนณใ
Code: https://github.com/SUFE-AIFLM-Lab/Fin-R1
๐ ็ฎๅฝ
๐ก ๅบๆฏๅบ็จ
Fin-R1 ๆฏไธๆฌพไธไธบ้่ๆจ็้ขๅ่ฎพ่ฎก็ๅคง่ฏญ่จๆจกๅ๏ผ้็จ่ฝป้ๅ็ 7B ๅๆฐ้็บงๆถๆใๅจๆพ่้ไฝ้จ็ฝฒๆๆฌ็ๅๆถ๏ผ่ฏฅๆจกๅ้่ฟๅจ้ๅฏน้่ๆจ็ๅบๆฏ็้ซ่ดจ้ๆ็ปด้พๆฐๆฎไธ้็จ SFT๏ผ็็ฃๅพฎ่ฐ๏ผๅ RL๏ผๅผบๅๅญฆไน ๏ผไธค้ถๆฎต่ฎญ็ป๏ผไธบๆจกๅๅจ้่้ขๅ็ๅบ็จๆไพไบๅๅฎ็็่ฎบๆฏๆใไธๅก่งๅใๅณ็ญ้ป่พไปฅๅๆๆฏๅฎ็ฐ่ฝๅ๏ผไป่ๆๆๆๅๆจกๅ็้่ๅคๆๆจ็่ฝๅ๏ผไธบ้ถ่กใ่ฏๅธใไฟ้ฉไปฅๅไฟกๆ็ญ้่ๆ ธๅฟไธๅกๅบๆฏๆไพๆๅๆฏๆใ
้่ไปฃ็
้่ไปฃ็ ๆฏๆๅจ้่้ขๅไธญ็จไบๅฎ็ฐๅ็ง้่ๆจกๅใ็ฎๆณๅๅๆไปปๅก็่ฎก็ฎๆบ็ผ็จไปฃ็ ๏ผๆถต็ไบไป็ฎๅ็่ดขๅก่ฎก็ฎๅฐๅคๆ็้่่ก็ๅๅฎไปทใ้ฃ้ฉ่ฏไผฐๅๆ่ต็ปๅไผๅ็ญๅคไธชๆน้ข๏ผไปฅๆนไพฟ้่ไธไธไบบๅฃซ่ฟ่กๆฐๆฎๅค็ใ็ป่ฎกๅๆใๆฐๅผ่ฎก็ฎๅๅฏ่งๅ็ญๅทฅไฝใ
้่่ฎก็ฎ
้่่ฎก็ฎๆฏๅฏน้่้ขๅ็ๅ็ง้ฎ้ข่ฟ่กๅฎ้ๅๆๅ่ฎก็ฎ็่ฟ็จ๏ผๅ
ถๆ ธๅฟๅจไบ้่ฟๅปบ็ซๆฐๅญฆๆจกๅๅ่ฟ็จๆฐๅผๆนๆณๆฅ่งฃๅณๅฎ้
้่้ฎ้ข๏ผๅฏไธบ้่ๅณ็ญๆไพ็งๅญฆไพๆฎ๏ผๅธฎๅฉ้่ๆบๆๅๆ่ต่
ๆดๅฅฝๅฐ็ฎก็้ฃ้ฉใไผๅ่ตๆบ้
็ฝฎๅๆ้ซๆ่ตๅๆฅ็ใ
่ฑ่ฏญ้่่ฎก็ฎ
่ฑ่ฏญ้่่ฎก็ฎๅผบ่ฐๅจ่ทจ่ฏญ่จ็ฏๅขไธไฝฟ็จ่ฑ่ฏญ่ฟ่ก้่ๆจกๅ็ๆๅปบๅ่ฎก็ฎ๏ผๅนถ่ฝๅคไปฅ่ฑ่ฏญๆฐๅ้่ๅๆๆฅๅๅไธๅฝ้
ๅ่ก่ฟ่กๆฒ้ไบคๆตใ
้่ๅฎๅ จๅ่ง
้่ๅฎๅ
จๅ่ง่็ฆไบ้ฒ่้่็ฏ็ฝชไธ้ตๅฎ็็ฎก่ฆๆฑ๏ผๅธฎๅฉไผไธๅปบ็ซๅฅๅ
จ็ๅ่ง็ฎก็ไฝ็ณป๏ผๅฎๆ่ฟ่กๅ่งๆฃๆฅๅๅฎก่ฎก๏ผ็กฎไฟไธๅกๆไฝ็ฌฆๅ็ธๅ
ณๆณ่ง่ฆๆฑใ
ๆบ่ฝ้ฃๆง
ๆบ่ฝ้ฃๆงๅฉ็จAIไธๅคงๆฐๆฎๆๆฏ่ฏๅซๅ็ฎก็้่้ฃ้ฉ๏ผไธไผ ็ป้ฃๆงๆๆฎต็ธๆฏ๏ผๆบ่ฝ้ฃๆงๅ
ทๆๆด้ซ็ๆ็ใๅ็กฎๆงๅๅฎๆถๆง๏ผๅฎ้่ฟๅฏนๆตท้้่ๆฐๆฎ็ๆทฑๅบฆๆๆๅๅๆ๏ผ่ฝๅคๅ็ฐๆฝๅจ็้ฃ้ฉๆจกๅผๅๅผๅธธไบคๆ่กไธบ๏ผไป่ๅๆถ้ข่ญฆๅ้ๅ็ธๅบ็้ฃ้ฉๆงๅถๆชๆฝใ
ESGๅๆ
ESGๅๆ้่ฟ่ฏไผฐไผไธๅจ็ฏๅข๏ผEnvironmental๏ผใ็คพไผ๏ผSocial๏ผใๆฒป็๏ผGovernance๏ผ็่กจ็ฐ๏ผ่กก้ๅ
ถๅฏๆ็ปญๅๅฑ่ฝๅ๏ผ็กฎไฟๆ่ตๆดปๅจไธไป
่ฝๅค่ทๅพ่ดขๅกๅๆฅ๏ผ่ฟ่ฝไฟ่ฟๅฏๆ็ปญๅๅฑๅ็คพไผ่ดฃไปป็ๅฑฅ่กใ้่ๆบๆๅไผไธไน้่ฟๆๅ่ช่บซ็ ESG ็ปฉๆ๏ผๆฅๆปก่ถณๆ่ต่
ๅ็คพไผๅฏนไผไธๆด้ซ็ๆๆๅ่ฆๆฑใ
ๆปไฝๅทฅไฝๆต็จ
ๆไปฌๅบไบ DeepSeek-R1 ๆๅปบไบๆฐๆฎ่ธ้ฆๆกๆถ๏ผๅนถไธฅๆ ผๆ็
งๅฎๆนๅๆฐ่ฎพๅฎ่ฟ่กๆฐๆฎๅค็๏ผ้็จไธค้ถๆฎตๆฐๆฎ็ญ้ๆนๆณๆๅ้่้ขๅๆฐๆฎ่ดจ้๏ผ็ๆไบSFTๆฐๆฎ้ๅRLๆฐๆฎ้ใๅจ่ฎญ็ป่ฟ็จไธญ๏ผๆไปฌๅฉ็จQwen2.5-7B-Instruct๏ผ้่ฟ็็ฃๅพฎ่ฐ๏ผSFT๏ผๅๅผบๅๅญฆไน ๏ผRL๏ผ่ฎญ็ป้่ๆจ็ๅคงๆจกๅ Fin-R1๏ผไปฅๆๅ้่ๆจ็ไปปๅก็ๅ็กฎๆงๅๆณๅ่ฝๅใ
๐ ๏ธ ๆฐๆฎๆๅปบ
ไธบๅฐ DeepSeek-R1 ็ๆจ็่ฝๅ่ฟ็งป่ณ้่ๅบๆฏๅนถ่งฃๅณ้ซ่ดจ้้่ๆจ็ๆฐๆฎ้ฎ้ข๏ผๆไปฌ็จDeepseek-R1๏ผๆปก่ก็๏ผ้ๅฏนๆถต็่กไธ่ฏญๆ๏ผFinCorpusใAnt_Finance๏ผ๏ผไธไธ่ฎค็ฅ๏ผFinPEE๏ผ๏ผไธๅก็ฅ่ฏ๏ผFinCUGEใFinanceIQใFinance-Instruct-500K๏ผ๏ผ่กจๆ ผ่งฃๆ๏ผFinQA๏ผ๏ผๅธๅบๆดๅฏ๏ผTFNS๏ผ๏ผๅค่ฝฎไบคไบ๏ผConvFinQA๏ผไปฅๅ้ๅๆ่ต๏ผFinanceQT๏ผ็ๅคไธชๆฐๆฎ้่ฟ่ก้ขๅ็ฅ่ฏ่ธ้ฆ็ญ้๏ผๆๅปบไบ็บฆ 60k ๆก้ขๅไธไธ้่ๆจ็ๅบๆฏ็้ซ่ดจ้ COT ๆฐๆฎ้ Fin-R1-Data ใ่ฏฅๆฐๆฎ้ๆถต็ไธญ่ฑๆ้่ๅ็ด้ขๅ็ๅค็ปดๅบฆไธไธ็ฅ่ฏ๏ผๅนถๆ นๆฎๅ ทไฝไปปๅกๅ ๅฎนๅฐๅ ถๅไธบ้่ไปฃ็ ใ้่ไธไธ็ฅ่ฏใ้่้ๆจ็็ฑปไธๅก็ฅ่ฏๅ้่ๆจ็็ฑปไธๅก็ฅ่ฏๅๅคงๆจกๅ๏ผๅฏๆๆๆฏๆ้ถ่กใๅบ้ๅ่ฏๅธ็ญๅคไธช้่ๆ ธๅฟๅบๆฏใๆฌ็ ็ฉถๆๅปบไบๅบไบ Deepseek-R1 ็ๆฐๆฎ่ธ้ฆๆกๆถ๏ผๅนถๅๆฐๆงๆๅบๅฏนๆ็ปด้พ่ฟ่กโ็ญๆก+ๆจ็โๅ่ฝฎ่ดจ้ๆๅ็ญ้ๆนๆณ๏ผ้ฆ่ฝฎๅบไบ่งๅๅน้ ๅ Qwen2.5-72B-Instruct ๅฏน็ญๆกๅ็กฎๆง่ฏๅ๏ผๆฌก่ฝฎๅฏนๆจ็้พ็้ป่พไธ่ดๆงใๆฏ่ฏญๅ่งๆง็ญๆจ็้ป่พ่ฟ่กๆทฑๅบฆๆ ก้ชไปฅไฟ่ฏๆฐๆฎ่ดจ้ใ
ๆฐๆฎ่ธ้ฆ
ๅจ่ธ้ฆ่ฟ็จไธญ๏ผๆไปฌไธฅๆ ผไพ็ ง DeepSeek - R1 ๅฎๆนๆไพ็็ป่๏ผ่ฟ่ก็ธๅบ่ฎพ็ฝฎ็ๆฐๆฎ่ธ้ฆๆไฝใ
ๆฐๆฎ็ญ้
้ๅฏน้่ๆฐๆฎ็ปๆ็ๅคๆ็นๆง้ๅๅฏนๆ็ปด้พ่ฟ่กโ็ญๆก+ๆจ็้ป่พโๅ่ฝฎ่ดจ้ๆๅ็ๅๆฐๆนๅผ็ญ้๏ผ้ฆ่ฝฎๅบไบ่งๅๅน้ ๅ Qwen2.5-72B-Instruct ๅฏน็ญๆกๅ็กฎๆง่ฏๅ๏ผๆฌก่ฝฎๅฏนๆจ็้พ็้ป่พไธ่ดๆงใๆฏ่ฏญๅ่งๆง็ญๆจ็้ป่พ่ฟ่กๆทฑๅบฆๆ ก้ชไปฅไฟ่ฏๆฐๆฎ่ดจ้๏ผๆฏๆฌกๆๅ็ญ้ๅบ็ๆฐๆฎๆ ๆณจไธบ good ๆ bad ่ฟ่กๅบๅ๏ผ
1๏ผ็ญๆกๆๅ๏ผๅฏนไบ่ธ้ฆๅพๅฐ็ๆฐๆฎ๏ผ้ๅฏนๅฎข่ง้ข๏ผๅฆ้ๆฉ้ขใๅคๆญ้ข๏ผ๏ผ้็จๅบไบ่งๅ็ๅน้ ๆนๅผ๏ผๆ กๅฏน่ธ้ฆๆฐๆฎ็ๆญฃ็กฎๆง๏ผๅฏนไบๆ ๆณ้่ฟ่งๅๅน้ ็็ปๆ๏ผๅฉ็จ Qwen2.5-72B-Instruct ๅฏนๆจกๅ็ๆ็็ญๆกไปฅๅๆญฃ็กฎ็ญๆก่ฟ่กๆๅ๏ผๆญฃ็กฎๅพ 1 ๅ๏ผ้่ฏฏๅพ 0 ๅใ
2๏ผๆจ็่ฟ็จๆๅ๏ผๅฏนไบ็ป่ฟไธไธๆญฅ็ญ้ๅพๅฐ็ๆญฃ็กฎๆ็ปด้พๆฐๆฎ๏ผๅๆฌกๅฉ็จ Qwen2.5-72B-Instruct ๅฏนๆจ็่ฝจ่ฟน่ฟ่กๆๅ๏ผ้ซ่ดจ้ๆฐๆฎๅพ 1 ๅ๏ผไฝ่ดจ้ๆฐๆฎๅพ 0 ๅใๆไปฌ้ๅไบๅฆไธๅ ไธชๆๆ ๆฅ่ฟ่กๆๅ๏ผ
1.ๅ ้จไธ่ดๆง๏ผๆฃๆฅๆจ็่ฟ็จไธญ็ๆญฅ้ชคๆฏๅฆไธ่ด๏ผๅนถไธๆฏๅฆ่ฝๅค้ๆญฅ้ป่พๅฐๆจๅฏผๅบๆ ๅ็ญๆกใ
2.ๆฏ่ฏญ้ๅ ๅบฆ๏ผๆฃๆฅๆจ็่ฟ็จไธญไฝฟ็จ็ๆฏ่ฏญไธๆ ๅ็ญๆกไธญ็ๆฏ่ฏญ็้ๅ ็จๅบฆใ้ๅ ๅบฆ่ถ้ซ่ถๅฅฝใ
3.ๆจ็ๆญฅ้ชคๆฐ้๏ผ่ฏไผฐๆจ็่ฟ็จๆฏๅฆๅ ๅซ่ถณๅค็ๆญฅ้ชค๏ผ่ณๅฐ3ๆญฅ๏ผใ
4.้ป่พไธ่ดๆง๏ผ็กฎไฟๆจ็่ฟ็จไธญ็ๆญฅ้ชคไธๆ ๅ็ญๆกๅจ้ป่พไธ้ซๅบฆไธ่ด๏ผๅนถๆฃๆฅๆฏๅฆๅญๅจๆๆพ็้่ฏฏๆ้ๆผใ
5.ๅ ๅฎนๅคๆ ทๆง๏ผๆฃๆฅๆจ็่ฟ็จไธญๆฏๅฆๅญๅจๅคง้้ๅค็ๆญฅ้ชคใ
6.ไธไปปๅก้ขๅ็็ธๅ ณๆง๏ผๆฃๆฅๆจ็่ฟ็จๆฏๅฆๆถๅไธไปปๅก้ขๅ็ธๅ ณ็ๅ ๅฎน๏ผไปปๅก้ขๅ๏ผ{task_domain}๏ผใๅฆๆๆจ็ๅๆ ไบไธไปปๅก้ขๅ็็ธๅ ณๆง๏ผๅ็ปไบๆด้ซ็่ฏๅใ
7.ไธไปปๅกๆไปค็ไธ่ดๆง๏ผๆฃๆฅๆจ็่ฟ็จๆฏๅฆไธไปปๅกๆไปค้ซๅบฆ็ธๅ ณใ็ธๅ ณๆง่ถ้ซ่ถๅฅฝใๅฆๆๆจ็ๅ ๅฎนๅฎๅ จ็ฌฆๅไปปๅกๆไปค๏ผๅ็ปไบๆด้ซ็่ฏๅใ
ๆไปฌๅฐ็ป่ฟไธค่ฝฎ็ญ้ๅๅๆ ๆณจไธบgood็ๆฐๆฎไฝไธบ้ซ่ดจ้็ COT ๆฐๆฎ็จไบ SFT ๏ผ่ๆช็ป่ฟ็ญ้ๆ ๆณจไธบbad็ๆฐๆฎๅไฝไธบๆจ็QAๆฐๆฎ็จไบๅผบๅๅญฆไน ๏ผRL๏ผใ
Fin-R1-Dataๆฐๆฎๅๅธๅฆไธ๏ผ
Fin-R1-Data ๆถต็ไธญ่ฑๆ้่ๅ็ด้ขๅ็ๅค็ปดๅบฆไธไธ็ฅ่ฏ๏ผๅนถๆ นๆฎๅ ทไฝไปปๅกๅ ๅฎนๅฐๅ ถๅไธบ้่ไปฃ็ ใ้่ไธไธ็ฅ่ฏใ้่้ๆจ็็ฑปไธๅก็ฅ่ฏๅ้่ๆจ็็ฑปไธๅก็ฅ่ฏๅๅคงๆจกๅ๏ผๅฏๆๆๆฏๆ้ถ่กใ่ฏๅธไปฅๅไฟกๆ็ญๅคไธช้่ๆ ธๅฟๅบๆฏใ
| ๆฐๆฎ้ | ๆฐๆฎ้ |
|---|---|
| ConvFinQA-R1-Distill | 7629 |
| Finance-Instruct-500K-R1-Distill | 11300 |
| FinCUGE-R1-Distill | 2000 |
| FinQA-R1-Distill | 2948 |
| TFNS-R1-Distill | 2451 |
| FinanceIQ-R1-Distill | 2596 |
| FinanceQT-R1-Distill | 152 |
| Ant_Finance-R1-Distill | 1548 |
| FinCorpus-R1-Distill | 29288 |
| FinPEE-R1-Distill | 179 |
| ๆป่ฎก | 60091 |
๐ ๅพฎ่ฐ่ฎญ็ป
ไธค้ถๆฎตๆต็จ
้ๅฏน้่้ขๅๅคๆๆจ็ไปปๅก๏ผๆไปฌๅฉ็จ Qwen2.5-7B-Instruct ่ฟ่กไธค้ถๆฎตๅพฎ่ฐ่ฎญ็ปๅพๅฐ้่ๆจ็ๅคง่ฏญ่จๆจกๅ Fin-R1 ใ้ฆๅ ้่ฟ้ซ่ดจ้้่ๆจ็ๆฐๆฎ็ SFT (Supervised Fine-Tuning) ๅธฎๅฉๆจกๅๅๆญฅๆๅ้่ๆจ็่ฝๅ๏ผ็ถๅๅจ GRPO๏ผGroup Relative Policy Optimization) ็ฎๆณ็ๅบ็กไธ็ปๅๆ ผๅผๅฅๅฑๅๅ็กฎๅบฆๅฅๅฑ่ฟ่กๅผบๅๅญฆไน ๏ผไปฅๆญค่ฟไธๆญฅๆๅ้่ๆจ็ไปปๅก็ๅ็กฎๆงๅๆณๅ่ฝๅใ
็ฌฌไธ้ถๆฎต----ๆจ็่ฝๅๆณจๅ ฅ๏ผ
้ๅฏน้่ๆจ็ไปปๅกไธญ็ๅคๆๆจ็๏ผๆไปฌ็ฌฌไธ้ถๆฎตไฝฟ็จ ConvFinQA ๅ FinQA ้่ๆฐๆฎ้ๅฏน Qwen2.5-7B-Instruct ่ฟ่กไบ็็ฃๅพฎ่ฐใ็ป่ฟไธ่ฝฎๅพฎ่ฐ่ฎญ็ป๏ผ็กฎไฟๆจกๅ่ฝๅคๆทฑๅ ฅ็่งฃๅนถๅค็ๅคๆ็้่ๆจ็้ฎ้ขใ
็ฌฌไบ้ถๆฎต----ๅผบๅๅญฆไน ไผๅ๏ผ
ๅจๆจกๅๆๆกๅคๆๆจ็ๆ่ฝๅ๏ผๆไปฌ้็จ GRPO๏ผGroup Relative Policy Optimization๏ผ็ฎๆณไฝไธบๆ ธๅฟๆกๆถ๏ผไปฅๅ้ๅฅๅฑๆบๅถไผๅๆจกๅ่พๅบ็ๆ ผๅผๅๅ็กฎๅบฆ๏ผๅนถๅจๆญคๅบ็กไธๅผๅ ฅไบๅบไบๆจกๅ็้ช่ฏๅจ๏ผModel-Based Verifier๏ผ๏ผ้็จ Qwen2.5-Max ่ฟ่ก็ญๆก่ฏไผฐๆฅๆน่ฟๅบไบๆญฃๅ่กจ่พพๅผ็ๅฅๅฑๅฏ่ฝๅญๅจ็ๅๅทฎ๏ผ็ๆๆดๅ ็ฒพ็กฎๅฏ้ ็ๅฅๅฑไฟกๅท๏ผไป่ๆๅๅผบๅๅญฆไน ็ๆๆๅ็จณๅฎๆงใ
๐จ ๆจกๅ่ฏๆต็ปๆ
ๆไปฌๅจ่ฆ็ๅค้กน้่ไธๅกๅบๆฏ็ๅบๅๆต่ฏไธๅฏนๆจกๅ่ฟ่ก่ฏไผฐ๏ผๅจ่ฏๆต็ปๆไธญ๏ผๅช็ป่ฟๆไปคๅพฎ่ฐ (SFT) ็ๆจกๅ Fin-R1-SFT ๅจ้่ๅบๆฏไธญ็ธ่พไบๅบ็กๆจกๅๅทฒ็ปๅๅพไบไธๅฎๆง่ฝๆๅ๏ผไฝๆฏ็ธๆฏไบ DeepSeek-R1 ไปๆๆๅ็ฉบ้ด๏ผๆไปฌไบๆฏๅจ Fin-R1-SFT ๅบ็กไธๅ่ฟ่กๅผบๅๅญฆไน ่ฎญ็ป๏ผ็ปๆๅ็ฐ็ป่ฟๆไปคๅพฎ่ฐ (SFT) ๅ ๅผบๅๅญฆไน (RL) ่ฎญ็ป็ Fin-R1 ไปฅไป 7B ็่ฝป้ๅๅๆฐ่งๆจกๅฑ็ฐๅบๆพ่็ๆง่ฝไผๅฟ๏ผ่พพๅฐ 75.2 ็ๅนณๅๅพๅไฝๅฑ ็ฌฌไบ๏ผๅ จ้ข่ถ ่ถๅ่ฏ็ๅ่งๆจกๆจกๅ๏ผๅๆถไธ่กไธๆ ๆ DeepSeek-R1 ๅนณๅๅๅทฎ่ทไป 3.0๏ผ ไธ่ถ ่ถDeepSeek-R1-Distill-Llama-70B๏ผ69.2๏ผ6.0ๅใๆญคๅค Fin-R1 ๅจ่็ฆ็ๅฎ้่่กจๆ ผๆฐๅผๆจ็ไปปๅก็ FinQA ไปฅๅๅค่ฝฎๆจ็ไบคไบๅบๆฏ็ ConvFinQA ไธคๅคงๅ ณ้ฎไปปๅกๆต่ฏไธๅๅซไปฅ 76.0 ๅ 85.0 ็ๅพๅๅจๅ่ฏๆจกๅไธญ็ป้กถ็ฌฌไธ๏ผๅฑ็ฐๅบไบๆจกๅๅจ้่ๆจ็ๅบๆฏๅ้่้ๆจ็ๅบๆฏไธญ็ๅผบๅคงๅค็่ฝๅใ
| Model | Parameters | FinQA | ConvFinQA | Ant_Finance | TFNS | Finance-Instruct-500k | Average |
|---|---|---|---|---|---|---|---|
| DeepSeek-R1 | 671B | 71.0 | 82.0 | 90.0 | 78.0 | 70.0 | 78.2 |
| Fin-R1 | 7B | 76.0 | 85.0 | 81.0 | 71.0 | 62.9 | 75.2 |
| Qwen-2.5-32B-Instruct | 32B | 72.0 | 78.0 | 84.0 | 77.0 | 58.0 | 73.8 |
| DeepSeek-R1-Distill-Qwen-32B | 32B | 70.0 | 72.0 | 87.0 | 79.0 | 54.0 | 72.4 |
| Fin-R1-SFT | 7B | 73.0 | 81.0 | 76.0 | 68.0 | 61.0 | 71.9 |
| Qwen-2.5-14B-Instruct | 14B | 68.0 | 77.0 | 84.0 | 72.0 | 56.0 | 71.4 |
| DeepSeek-R1-Distill-Llama-70B | 70B | 68.0 | 74.0 | 84.0 | 62.0 | 56.0 | 69.2 |
| DeepSeek-R1-Distill-Qwen-14B | 14B | 62.0 | 73.0 | 82.0 | 65.0 | 49.0 | 66.2 |
| Qwen-2.5-7B-Instruct | 7B | 60.0 | 66.0 | 85.0 | 68.0 | 49.0 | 65.6 |
| DeepSeek-R1-Distill-Qwen-7B | 7B | 55.0 | 62.0 | 71.0 | 60.0 | 42.0 | 58.0 |
ๅฃฐๆๅๆชๆฅๅฑๆ
ๆฌ้กน็ฎ็ฑไธๆตท่ดข็ปๅคงๅญฆ็ป่ฎกไธๆฐๆฎ็งๅญฆๅญฆ้ข้่ๅคง่ฏญ่จๆจกๅ่ฏพ้ข็ป๏ผSUFE-AIFLM-Lab๏ผ่ๅ่ดข่ทๆ่พฐๅฎๆใFin-R1 ไฝไธบ้่้ขๅ็ๆจ็ๅๅคง่ฏญ่จๆจกๅ๏ผ่ฝ่ฝๅบ่ฒๅฎๆ่ฏธๅค้่ไปปๅก๏ผไธบ็จๆทๆไพไธไธๆๅก๏ผไฝ็ฐ้ถๆฎตไปๅญๅจๆๆฏ็ถ้ขไธๅบ็จ้ๅถใๅฎๆไพ็ๅปบ่ฎฎๅๅๆ็ปๆไป ไพๅ่๏ผไธๅฏ็ญๅไบไธไธ้่ๅๆๅธๆไธๅฎถ็็ฒพๅๅคๆญใๆไปฌ่ฏๆๅธๆ็จๆทไปฅๆนๅคๆงๆ็ปดๅฎก่งๆจกๅ่พๅบ๏ผ็ปๅ่ช่บซไธไธ็ฅ่ฏไธ็ป้ช่ฟ่กๅณ็ญใๅฏนไบๆชๆฅ๏ผๆไปฌๅฐๆ็ปญไผๅ Fin-R1๏ผๆทฑๅบฆๆข็ดขๅ ถๅจๅๆฒฟ้่ๅบๆฏ็ๅบ็จๆฝๅ๏ผๅฉๅ้่่กไธ่ฟๅๆบ่ฝๅไธๅ่งๅ็ๆฐ้ซๅบฆ๏ผไธบ่กไธๅๅฑๆณจๅ ฅๅผบๅฒๅจๅใ
๐ซ ่็ณปๆไปฌ
่ฏ้ไธ็ๅไปๅ ฑๅๆข็ดข AI ไธ้่ๆทฑๅบฆ่ๅ็ๅๆฐ่ๅผ๏ผๅ ฑๅปบๆบๆ ง้่ๆฐ็ๆ๏ผๅนถ้่ฟ้ฎไปถไธzhang.liwen@shufe.edu.cn่็ณป
- Downloads last month
- 684
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp# Start a local OpenAI-compatible server: llama serve -hf Mungert/Fin-R1-GGUF: