andy-lzjtu/Qwen3-8B_MapFinBen

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 20, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

The andy-lzjtu/Qwen3-8B_MapFinBen is an 8 billion parameter Qwen3 model fine-tuned specifically for the MapFinBen financial benchmark. This model is designed to excel in financial domain tasks, leveraging its specialized training to provide accurate and relevant responses. It utilizes a 32,768 token context length, making it suitable for processing extensive financial documents and data. Its primary strength lies in its optimized performance for financial analysis and related applications.

Loading preview...

Model Overview

The andy-lzjtu/Qwen3-8B_MapFinBen is an 8 billion parameter Qwen3 model that has been specifically fine-tuned for the MapFinBen financial benchmark. This specialization means the model is optimized for tasks within the financial domain, aiming to provide high-accuracy results for financial analysis and related applications.

Key Features

  • Base Model: Qwen3-8B architecture.
  • Domain Specialization: Fine-tuned for the MapFinBen financial benchmark, enhancing its performance on financial tasks.
  • Context Length: Supports a 32,768 token context window, allowing for the processing of substantial financial texts.
  • Ollama Compatibility: Includes Hugging Face model weights, tokenizer files, and Ollama-compatible template files for easy integration and deployment.

Recommended Usage

For deterministic evaluation, the model suggests specific settings:

  • temperature: 0.0
  • top_p: 1.0
  • seed: 42
  • stop sequences: <|im_end|>, <|endoftext|>

The provided template.tmpl defines a simple ChatML prompt format, avoiding complex Qwen3 thinking/tool templates, making it straightforward for benchmark conversions and general use.