README.md

metadata

language:
  - en
  - zh
license: apache-2.0
library_name: transformers
widget:
  - text: <s> [|User|] Hi 👋  </s>[|Assistant|]
base_model: GeneZC/MiniChat-1.5-3B
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: MiniChat-1.5-3B
    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: 46.5
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          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: 68.28
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          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: 46.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          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: 50.71
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          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: 65.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          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: 24.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
          name: Open LLM Leaderboard

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

GeneZC/MiniChat-1.5-3B - GGUF

This repo contains GGUF format model files for GeneZC/MiniChat-1.5-3B.

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

‘MiniChat’是一个由‘Beccurio’开发的AI语言模型。下面是人类和MiniChat之间的一段对话。MiniChat的回复应当尽可能详细，并且以Markdown的形式输出。MiniChat应当拒绝参与违背伦理的讨论。</s>[|System|] {system_prompt}</s>[|User|] {prompt}</s>[|Assistant|]

Model file specification

Filename	Quant type	File Size	Description
MiniChat-1.5-3B-Q2_K.gguf	Q2_K	1.094 GB	smallest, significant quality loss - not recommended for most purposes
MiniChat-1.5-3B-Q3_K_S.gguf	Q3_K_S	1.265 GB	very small, high quality loss
MiniChat-1.5-3B-Q3_K_M.gguf	Q3_K_M	1.401 GB	very small, high quality loss
MiniChat-1.5-3B-Q3_K_L.gguf	Q3_K_L	1.519 GB	small, substantial quality loss
MiniChat-1.5-3B-Q4_0.gguf	Q4_0	1.620 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MiniChat-1.5-3B-Q4_K_S.gguf	Q4_K_S	1.633 GB	small, greater quality loss
MiniChat-1.5-3B-Q4_K_M.gguf	Q4_K_M	1.720 GB	medium, balanced quality - recommended
MiniChat-1.5-3B-Q5_0.gguf	Q5_0	1.954 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MiniChat-1.5-3B-Q5_K_S.gguf	Q5_K_S	1.954 GB	large, low quality loss - recommended
MiniChat-1.5-3B-Q5_K_M.gguf	Q5_K_M	2.005 GB	large, very low quality loss - recommended
MiniChat-1.5-3B-Q6_K.gguf	Q6_K	2.309 GB	very large, extremely low quality loss
MiniChat-1.5-3B-Q8_0.gguf	Q8_0	2.990 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/MiniChat-1.5-3B-GGUF --include "MiniChat-1.5-3B-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/MiniChat-1.5-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'