README.md · tensorblock/Yi-34B-200K-AEZAKMI-RAW-1701-GGUF at main

metadata

license: apache-2.0
tags:
  - finetune
  - fine tune
  - dpo
  - sft
  - yi
  - TensorBlock
  - GGUF
base_model: adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
model-index:
  - name: Yi-34B-200K-AEZAKMI-RAW-1701
    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: 66.81
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          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: 85.79
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          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: 75.44
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          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: 57.91
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          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: 80.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          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: 59.97
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
          name: Open LLM Leaderboard

adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 - GGUF

This repo contains GGUF format model files for adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701.

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
Yi-34B-200K-AEZAKMI-RAW-1701-Q2_K.gguf	Q2_K	12.825 GB	smallest, significant quality loss - not recommended for most purposes
Yi-34B-200K-AEZAKMI-RAW-1701-Q3_K_S.gguf	Q3_K_S	14.960 GB	very small, high quality loss
Yi-34B-200K-AEZAKMI-RAW-1701-Q3_K_M.gguf	Q3_K_M	16.655 GB	very small, high quality loss
Yi-34B-200K-AEZAKMI-RAW-1701-Q3_K_L.gguf	Q3_K_L	18.139 GB	small, substantial quality loss
Yi-34B-200K-AEZAKMI-RAW-1701-Q4_0.gguf	Q4_0	19.467 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Yi-34B-200K-AEZAKMI-RAW-1701-Q4_K_S.gguf	Q4_K_S	19.599 GB	small, greater quality loss
Yi-34B-200K-AEZAKMI-RAW-1701-Q4_K_M.gguf	Q4_K_M	20.659 GB	medium, balanced quality - recommended
Yi-34B-200K-AEZAKMI-RAW-1701-Q5_0.gguf	Q5_0	23.708 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Yi-34B-200K-AEZAKMI-RAW-1701-Q5_K_S.gguf	Q5_K_S	23.708 GB	large, low quality loss - recommended
Yi-34B-200K-AEZAKMI-RAW-1701-Q5_K_M.gguf	Q5_K_M	24.322 GB	large, very low quality loss - recommended
Yi-34B-200K-AEZAKMI-RAW-1701-Q6_K.gguf	Q6_K	28.214 GB	very large, extremely low quality loss
Yi-34B-200K-AEZAKMI-RAW-1701-Q8_0.gguf	Q8_0	36.542 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-34B-200K-AEZAKMI-RAW-1701-GGUF --include "Yi-34B-200K-AEZAKMI-RAW-1701-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-34B-200K-AEZAKMI-RAW-1701-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'