KexuanShi/sft_gemma2_2b_layerdrop_p040
TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.6BQuant:BF16Context Size:8kPublished:Oct 5, 2026Architecture:Transformer Featherless Exclusive Cold
KexuanShi/sft_gemma2_2b_layerdrop_p040 is a 2.6 billion parameter instruction-tuned language model, fine-tuned from an unspecified base model using the TRL library. This model was trained with Supervised Fine-Tuning (SFT) and supports a context length of 8192 tokens. Its primary use case is text generation based on user prompts, demonstrating capabilities in conversational AI.
Loading preview...
Overview
KexuanShi/sft_gemma2_2b_layerdrop_p040 is a 2.6 billion parameter language model that has undergone Supervised Fine-Tuning (SFT). It is built upon an unspecified base model and leverages the TRL library for its training process. The model supports a context length of 8192 tokens, making it suitable for processing moderately long inputs.
Key Capabilities
- Instruction-following text generation: The model is fine-tuned to generate responses based on user prompts, as demonstrated by its quick start example for conversational questions.
- TRL-based training: Utilizes the Transformers Reinforcement Learning (TRL) library, indicating a focus on fine-tuning for specific tasks or behaviors.
Good for
- Conversational AI applications: Its instruction-following nature makes it suitable for chatbots or interactive text generation tasks where a model needs to respond coherently to user queries.
- Exploration of SFT models: Developers interested in models fine-tuned with SFT using the TRL framework can use this as a reference or starting point.