--- language: - en - ko library_name: transformers tags: - pytorch - Yi-Ko - 01-ai - Yi - TensorBlock - GGUF extra_gated_heading: Access beomi/Yi-Ko-6B on Hugging Face extra_gated_button_content: Submit extra_gated_fields: I agree to share my name, email address and username: checkbox ? I confirm that I understand this project is for research purposes only, and confirm that I agree to follow the LICENSE of this model : checkbox pipeline_tag: text-generation inference: false license: apache-2.0 base_model: beomi/Yi-Ko-6B model-index: - name: Yi-Ko-6B 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: 48.89 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B 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: 74.48 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B 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: 55.72 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B 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: 37.09 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B 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: 72.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B 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: 12.51 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beomi/Yi-Ko-6B name: Open LLM Leaderboard ---
TensorBlock

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

## beomi/Yi-Ko-6B - GGUF This repo contains GGUF format model files for [beomi/Yi-Ko-6B](https://huggingface.co/beomi/Yi-Ko-6B). 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 ``` ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [Yi-Ko-6B-Q2_K.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q2_K.gguf) | Q2_K | 2.240 GB | smallest, significant quality loss - not recommended for most purposes | | [Yi-Ko-6B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q3_K_S.gguf) | Q3_K_S | 2.592 GB | very small, high quality loss | | [Yi-Ko-6B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q3_K_M.gguf) | Q3_K_M | 2.857 GB | very small, high quality loss | | [Yi-Ko-6B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q3_K_L.gguf) | Q3_K_L | 3.084 GB | small, substantial quality loss | | [Yi-Ko-6B-Q4_0.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q4_0.gguf) | Q4_0 | 3.317 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [Yi-Ko-6B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q4_K_S.gguf) | Q4_K_S | 3.339 GB | small, greater quality loss | | [Yi-Ko-6B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q4_K_M.gguf) | Q4_K_M | 3.498 GB | medium, balanced quality - recommended | | [Yi-Ko-6B-Q5_0.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q5_0.gguf) | Q5_0 | 3.999 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [Yi-Ko-6B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q5_K_S.gguf) | Q5_K_S | 3.999 GB | large, low quality loss - recommended | | [Yi-Ko-6B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q5_K_M.gguf) | Q5_K_M | 4.092 GB | large, very low quality loss - recommended | | [Yi-Ko-6B-Q6_K.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q6_K.gguf) | Q6_K | 4.724 GB | very large, extremely low quality loss | | [Yi-Ko-6B-Q8_0.gguf](https://huggingface.co/tensorblock/Yi-Ko-6B-GGUF/tree/main/Yi-Ko-6B-Q8_0.gguf) | Q8_0 | 6.117 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/Yi-Ko-6B-GGUF --include "Yi-Ko-6B-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/Yi-Ko-6B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```