README.md

metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - chat
  - qwen
  - qwen2
  - finetune
  - chatml
  - OpenHermes-2.5
  - HelpSteer2
  - Orca
  - SlimOrca
  - TensorBlock
  - GGUF
base_model: MaziyarPanahi/calme-2.2-qwen2-7b
datasets:
  - nvidia/HelpSteer2
  - teknium/OpenHermes-2.5
  - microsoft/orca-math-word-problems-200k
  - Open-Orca/SlimOrca
pipeline_tag: text-generation
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
  - name: calme-2.2-qwen2-7b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 35.97
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 33.11
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 19.34
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 5.48
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 13.28
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 32.21
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.2-qwen2-7b
          name: Open LLM Leaderboard

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

MaziyarPanahi/calme-2.2-qwen2-7b - GGUF

This repo contains GGUF format model files for MaziyarPanahi/calme-2.2-qwen2-7b.

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

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
calme-2.2-qwen2-7b-Q2_K.gguf	Q2_K	2.809 GB	smallest, significant quality loss - not recommended for most purposes
calme-2.2-qwen2-7b-Q3_K_S.gguf	Q3_K_S	3.253 GB	very small, high quality loss
calme-2.2-qwen2-7b-Q3_K_M.gguf	Q3_K_M	3.547 GB	very small, high quality loss
calme-2.2-qwen2-7b-Q3_K_L.gguf	Q3_K_L	3.808 GB	small, substantial quality loss
calme-2.2-qwen2-7b-Q4_0.gguf	Q4_0	4.127 GB	legacy; small, very high quality loss - prefer using Q3_K_M
calme-2.2-qwen2-7b-Q4_K_S.gguf	Q4_K_S	4.152 GB	small, greater quality loss
calme-2.2-qwen2-7b-Q4_K_M.gguf	Q4_K_M	4.361 GB	medium, balanced quality - recommended
calme-2.2-qwen2-7b-Q5_0.gguf	Q5_0	4.950 GB	legacy; medium, balanced quality - prefer using Q4_K_M
calme-2.2-qwen2-7b-Q5_K_S.gguf	Q5_K_S	4.950 GB	large, low quality loss - recommended
calme-2.2-qwen2-7b-Q5_K_M.gguf	Q5_K_M	5.071 GB	large, very low quality loss - recommended
calme-2.2-qwen2-7b-Q6_K.gguf	Q6_K	5.825 GB	very large, extremely low quality loss
calme-2.2-qwen2-7b-Q8_0.gguf	Q8_0	7.542 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/calme-2.2-qwen2-7b-GGUF --include "calme-2.2-qwen2-7b-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/calme-2.2-qwen2-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'