yuxuanw8/qwen3b-racpo-v3-hotpot-checkpoint-3

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 8, 2026Architecture:Transformer Featherless Exclusive Cold

The yuxuanw8/qwen3b-racpo-v3-hotpot-checkpoint-3 is a 3.1 billion parameter language model, likely based on the Qwen architecture, fine-tuned for specific tasks. While specific details on its training and primary differentiators are not provided in the available information, its parameter count suggests it is suitable for applications requiring a balance of performance and computational efficiency. This model is intended for use cases where a moderately sized language model can be effectively deployed.

Loading preview...

Model Overview

This model, yuxuanw8/qwen3b-racpo-v3-hotpot-checkpoint-3, is a 3.1 billion parameter language model. The model card indicates it is a Hugging Face Transformers model, automatically generated, but lacks specific details regarding its architecture, development, or training data. The name suggests a potential fine-tuning for tasks related to "Hotpot" (possibly HotpotQA, a question answering dataset) and utilizing a "RACPO" (Reinforcement Learning from AI Feedback with Contrastive Preference Optimization) training methodology, which would imply a focus on improved alignment and response quality.

Key Characteristics

  • Parameter Count: 3.1 billion parameters, offering a balance between model capability and computational demands.
  • Context Length: Supports a context window of 32768 tokens, allowing for processing of relatively long inputs.
  • Potential Fine-tuning: The model name implies fine-tuning for specific tasks, possibly related to question answering or reasoning, using advanced reinforcement learning techniques.

Intended Use Cases

Given the limited information, this model is likely suitable for:

  • Research and Experimentation: Exploring the effects of RACPO fine-tuning on Qwen-based models.
  • Specific NLP Tasks: If the "Hotpot" in its name refers to HotpotQA, it could be well-suited for complex multi-hop question answering.
  • Applications requiring moderate-sized LLMs: For scenarios where larger models are too resource-intensive, but a capable language model is needed.

Finetunes
3 models