README.md

metadata

language:
  - ja
  - en
license: llama2
datasets:
  - databricks/databricks-dolly-15k
  - kunishou/databricks-dolly-15k-ja
  - izumi-lab/llm-japanese-dataset
thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
inference: false
base_model: rinna/youri-7b-chat
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: youri-7b-chat
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 51.19
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 76.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 46.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.17
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 75.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 1.52
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rinna/youri-7b-chat
          name: Open LLM Leaderboard

rinna/youri-7b-chat - GGUF

This repo contains GGUF format model files for rinna/youri-7b-chat.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
youri-7b-chat-Q2_K.gguf	Q2_K	2.533 GB	smallest, significant quality loss - not recommended for most purposes
youri-7b-chat-Q3_K_S.gguf	Q3_K_S	2.948 GB	very small, high quality loss
youri-7b-chat-Q3_K_M.gguf	Q3_K_M	3.298 GB	very small, high quality loss
youri-7b-chat-Q3_K_L.gguf	Q3_K_L	3.597 GB	small, substantial quality loss
youri-7b-chat-Q4_0.gguf	Q4_0	3.826 GB	legacy; small, very high quality loss - prefer using Q3_K_M
youri-7b-chat-Q4_K_S.gguf	Q4_K_S	3.857 GB	small, greater quality loss
youri-7b-chat-Q4_K_M.gguf	Q4_K_M	4.081 GB	medium, balanced quality - recommended
youri-7b-chat-Q5_0.gguf	Q5_0	4.652 GB	legacy; medium, balanced quality - prefer using Q4_K_M
youri-7b-chat-Q5_K_S.gguf	Q5_K_S	4.652 GB	large, low quality loss - recommended
youri-7b-chat-Q5_K_M.gguf	Q5_K_M	4.783 GB	large, very low quality loss - recommended
youri-7b-chat-Q6_K.gguf	Q6_K	5.529 GB	very large, extremely low quality loss
youri-7b-chat-Q8_0.gguf	Q8_0	7.161 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/youri-7b-chat-GGUF --include "youri-7b-chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/youri-7b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'