epinnock/deepseek-coder-6.7-evol-feedback-10k-v2
TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kPublished:Jan 28, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The epinnock/deepseek-coder-6.7-evol-feedback-10k-v2 is a 7 billion parameter language model developed by epinnock, fine-tuned from deepseek-ai/deepseek-coder-6.7b-instruct. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x speed improvement during training. It is designed for code-related tasks, leveraging its base model's capabilities in code generation and understanding.
Loading preview...
Overview
The epinnock/deepseek-coder-6.7-evol-feedback-10k-v2 is a 7 billion parameter language model developed by epinnock. It is a fine-tuned version of the deepseek-ai/deepseek-coder-6.7b-instruct model, indicating its specialization in code-related tasks and instruction following.
Key Capabilities
- Code Instruction Following: Inherits and enhances the instruction-following capabilities for coding tasks from its base model.
- Efficient Training: This model was trained significantly faster, achieving a 2x speedup, by utilizing the Unsloth library in conjunction with Huggingface's TRL library. This suggests an optimized training process.
Good For
- Code Generation: Ideal for tasks requiring the generation of code based on instructions.
- Code Understanding: Suitable for applications involving the interpretation and analysis of code.
- Instruction-based Coding: Effective in scenarios where specific coding instructions need to be followed precisely.