h2oai/h2ogpt-gm-7b-mistral-chat-sft-dpo-rag-v1

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Jan 29, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The h2oai/h2ogpt-gm-7b-mistral-chat-sft-dpo-rag-v1 is a 7 billion parameter language model developed by H2O.ai, fine-tuned from the Mistral-7B-v0.1 base model. This model is specifically optimized for chat-based interactions, leveraging Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval Augmented Generation (RAG) techniques. It is designed to provide conversational responses and can be integrated into applications requiring interactive AI, supporting a context length of 8192 tokens.

Loading preview...

Model Overview

The h2oai/h2ogpt-gm-7b-mistral-chat-sft-dpo-rag-v1 is a 7 billion parameter language model developed by H2O.ai using H2O LLM Studio. It is built upon the mistralai/Mistral-7B-v0.1 base model and has undergone Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval Augmented Generation (RAG) to enhance its conversational capabilities.

Key Capabilities

  • Chat-optimized responses: Fine-tuned for engaging in interactive conversations.
  • Mistral architecture: Leverages the efficient Mistral model architecture for performance.
  • Flexible deployment: Supports quantization (8-bit, 4-bit) and sharding across multiple GPUs for efficient resource utilization.
  • Standard chat templating: Compatible with Hugging Face Tokenizer's chat template for structured message formatting.

Intended Use Cases

This model is suitable for applications requiring:

  • General-purpose chatbots.
  • Conversational AI interfaces.
  • Interactive question-answering systems.
  • Integration into RAG-based applications for enhanced factual grounding.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p