--- 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 ---
TensorBlock

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](https://huggingface.co/MaziyarPanahi/calme-2.2-qwen2-7b). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d). ## 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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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](https://huggingface.co/tensorblock/calme-2.2-qwen2-7b-GGUF/tree/main/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 ```shell pip install -U "huggingface_hub[cli]" ``` Then, downoad the individual model file the a local directory ```shell 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: ```shell huggingface-cli download tensorblock/calme-2.2-qwen2-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```