README.md

metadata

license: cc
base_model: Walmart-the-bag/Yi-6B-Infinity-Chat
inference: false
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: Yi-6B-Infinity-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: 56.57
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-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: 77.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-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: 64.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-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: 50.75
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-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: 73.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-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: 36.01
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
          name: Open LLM Leaderboard

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

Walmart-the-bag/Yi-6B-Infinity-Chat - GGUF

This repo contains GGUF format model files for Walmart-the-bag/Yi-6B-Infinity-Chat.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Yi-6B-Infinity-Chat-Q2_K.gguf	Q2_K	2.177 GB	smallest, significant quality loss - not recommended for most purposes
Yi-6B-Infinity-Chat-Q3_K_S.gguf	Q3_K_S	2.523 GB	very small, high quality loss
Yi-6B-Infinity-Chat-Q3_K_M.gguf	Q3_K_M	2.788 GB	very small, high quality loss
Yi-6B-Infinity-Chat-Q3_K_L.gguf	Q3_K_L	3.015 GB	small, substantial quality loss
Yi-6B-Infinity-Chat-Q4_0.gguf	Q4_0	3.241 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Yi-6B-Infinity-Chat-Q4_K_S.gguf	Q4_K_S	3.263 GB	small, greater quality loss
Yi-6B-Infinity-Chat-Q4_K_M.gguf	Q4_K_M	3.422 GB	medium, balanced quality - recommended
Yi-6B-Infinity-Chat-Q5_0.gguf	Q5_0	3.916 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Yi-6B-Infinity-Chat-Q5_K_S.gguf	Q5_K_S	3.916 GB	large, low quality loss - recommended
Yi-6B-Infinity-Chat-Q5_K_M.gguf	Q5_K_M	4.009 GB	large, very low quality loss - recommended
Yi-6B-Infinity-Chat-Q6_K.gguf	Q6_K	4.633 GB	very large, extremely low quality loss
Yi-6B-Infinity-Chat-Q8_0.gguf	Q8_0	6.000 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/Yi-6B-Infinity-Chat-GGUF --include "Yi-6B-Infinity-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/Yi-6B-Infinity-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'