--- pipeline_tag: text-generation license: other language: - en tags: - math - TensorBlock - GGUF datasets: - internlm/Lean-Workbook - internlm/Lean-Github base_model: internlm/internlm2_5-step-prover --- <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"> Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a> </p> </div> </div> ## internlm/internlm2_5-step-prover - GGUF This repo contains GGUF format model files for [internlm/internlm2_5-step-prover](https://huggingface.co/internlm/internlm2_5-step-prover). 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). <div style="text-align: left; margin: 20px 0;"> <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;"> Run them on the TensorBlock client using your local machine ↗ </a> </div> ## Prompt template ``` <s><|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 | | -------- | ---------- | --------- | ----------- | | [internlm2_5-step-prover-Q2_K.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q2_K.gguf) | Q2_K | 3.005 GB | smallest, significant quality loss - not recommended for most purposes | | [internlm2_5-step-prover-Q3_K_S.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q3_K_S.gguf) | Q3_K_S | 3.476 GB | very small, high quality loss | | [internlm2_5-step-prover-Q3_K_M.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q3_K_M.gguf) | Q3_K_M | 3.830 GB | very small, high quality loss | | [internlm2_5-step-prover-Q3_K_L.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q3_K_L.gguf) | Q3_K_L | 4.133 GB | small, substantial quality loss | | [internlm2_5-step-prover-Q4_0.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q4_0.gguf) | Q4_0 | 4.453 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [internlm2_5-step-prover-Q4_K_S.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q4_K_S.gguf) | Q4_K_S | 4.485 GB | small, greater quality loss | | [internlm2_5-step-prover-Q4_K_M.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q4_K_M.gguf) | Q4_K_M | 4.713 GB | medium, balanced quality - recommended | | [internlm2_5-step-prover-Q5_0.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q5_0.gguf) | Q5_0 | 5.373 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [internlm2_5-step-prover-Q5_K_S.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q5_K_S.gguf) | Q5_K_S | 5.373 GB | large, low quality loss - recommended | | [internlm2_5-step-prover-Q5_K_M.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q5_K_M.gguf) | Q5_K_M | 5.507 GB | large, very low quality loss - recommended | | [internlm2_5-step-prover-Q6_K.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q6_K.gguf) | Q6_K | 6.350 GB | very large, extremely low quality loss | | [internlm2_5-step-prover-Q8_0.gguf](https://huggingface.co/tensorblock/internlm2_5-step-prover-GGUF/blob/main/internlm2_5-step-prover-Q8_0.gguf) | Q8_0 | 8.224 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/internlm2_5-step-prover-GGUF --include "internlm2_5-step-prover-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/internlm2_5-step-prover-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```