chohtet/Qwen2.5-14B-Instruct-H3-VLLM-test

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:Sep 27, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

chohtet/Qwen2.5-14B-Instruct-H3-VLLM-test is a 14.8 billion parameter instruction-tuned causal language model developed by chohtet. This model is fine-tuned from unsloth/Qwen2.5-14B-Instruct-bnb-4bit and was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It supports a context length of 32768 tokens and is suitable for general instruction-following tasks where efficient training and a substantial context window are beneficial.

Loading preview...

Overview

chohtet/Qwen2.5-14B-Instruct-H3-VLLM-test is a 14.8 billion parameter instruction-tuned language model developed by chohtet. It is fine-tuned from the unsloth/Qwen2.5-14B-Instruct-bnb-4bit model, leveraging the Qwen2.5 architecture. This model was specifically trained using the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x acceleration in the training process.

Key Capabilities

  • Instruction Following: Designed to accurately follow user instructions for various natural language processing tasks.
  • Efficient Training: Benefits from optimizations provided by Unsloth, allowing for faster fine-tuning compared to traditional methods.
  • Substantial Context Window: Supports a context length of 32768 tokens, enabling the processing of longer inputs and more complex conversations.

Good For

  • Developers seeking a robust 14.8B parameter model for general instruction-following applications.
  • Use cases requiring a model with a large context window to handle extensive textual data.
  • Scenarios where efficient fine-tuning and deployment are critical, leveraging the Unsloth-optimized training.