deepjoysur/LTM-SFR-RUN-1
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 13, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
deepjoysur/LTM-SFR-RUN-1 is a 7.6 billion parameter instruction-tuned causal language model developed by deepjoysur. It is finetuned from unsloth/qwen2.5-coder-7b-instruct-bnb-4bit, leveraging Unsloth for 2x faster training. This model is primarily optimized for coding tasks, building upon its base model's capabilities in code generation and understanding.
Loading preview...
deepjoysur/LTM-SFR-RUN-1 Overview
deepjoysur/LTM-SFR-RUN-1 is a 7.6 billion parameter instruction-tuned language model, developed by deepjoysur. It is finetuned from the unsloth/qwen2.5-coder-7b-instruct-bnb-4bit base model, indicating a strong focus on coding-related applications. The training process utilized Unsloth and Huggingface's TRL library, which enabled a 2x faster finetuning speed.
Key Capabilities
- Code-centric tasks: Inherits and enhances the coding capabilities from its base model, making it suitable for various programming-related applications.
- Efficient training: Benefits from Unsloth's optimization, allowing for quicker adaptation and iteration.
Good for
- Code generation: Generating programming code snippets or functions.
- Code understanding: Assisting with code analysis, explanation, or debugging.
- Developer tools: Integration into IDEs or other development workflows requiring a code-aware LLM.