MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Jan 16, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 is a 7 billion parameter language model created by MaziyarPanahi, merging Mistral-7B-Instruct-v0.1 and japanese-stablelm-instruct-gamma-7b. This model leverages the strengths of both base models, combining Mistral's general instruction following with Stability AI's Japanese language capabilities. It is designed for tasks requiring robust instruction adherence and strong performance in Japanese language contexts, with a context length of 4096 tokens.

Loading preview...

Model Overview

MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 is a 7 billion parameter instruction-tuned language model. It is a merged model, combining the foundational strengths of Mistral-7B-Instruct-v0.1 from Mistral AI with japanese-stablelm-instruct-gamma-7b from Stability AI. This merge aims to create a model that benefits from Mistral's general instruction-following abilities while enhancing its proficiency in Japanese language tasks.

Key Capabilities

  • Hybrid Architecture: Integrates two distinct 7B models to combine their respective strengths.
  • Instruction Following: Inherits instruction-tuning capabilities from both Mistral-7B-Instruct-v0.1 and japanese-stablelm-instruct-gamma-7b.
  • Multilingual Potential: Designed to perform well in both general English contexts (via Mistral) and specific Japanese language applications (via japanese-stablelm).
  • Merge Method: Utilizes the slerp (spherical linear interpolation) merge method, with specific parameter weighting applied to self-attention and MLP layers to balance contributions from each base model.

Use Cases

This model is suitable for developers looking for a 7B parameter model that:

  • Requires strong instruction adherence in general conversational or task-oriented scenarios.
  • Needs enhanced performance and fluency in generating or understanding Japanese text.
  • Can be deployed in applications where a balance between general-purpose AI and specific language expertise is beneficial.

Finetunes
2 models