--- language: - en pipeline_tag: text-generation inference: false tags: - facebook - meta - pytorch - llama - llama-2 - TensorBlock - GGUF base_model: philschmid/Llama-2-7b-hf ---
TensorBlock

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

## philschmid/Llama-2-7b-hf - GGUF This repo contains GGUF format model files for [philschmid/Llama-2-7b-hf](https://huggingface.co/philschmid/Llama-2-7b-hf). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
Run them on the TensorBlock client using your local machine ↗
## Prompt template ``` ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [Llama-2-7b-hf-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes | | [Llama-2-7b-hf-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q3_K_S.gguf) | Q3_K_S | 2.948 GB | very small, high quality loss | | [Llama-2-7b-hf-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q3_K_M.gguf) | Q3_K_M | 3.298 GB | very small, high quality loss | | [Llama-2-7b-hf-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q3_K_L.gguf) | Q3_K_L | 3.597 GB | small, substantial quality loss | | [Llama-2-7b-hf-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q4_0.gguf) | Q4_0 | 3.826 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [Llama-2-7b-hf-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q4_K_S.gguf) | Q4_K_S | 3.857 GB | small, greater quality loss | | [Llama-2-7b-hf-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q4_K_M.gguf) | Q4_K_M | 4.081 GB | medium, balanced quality - recommended | | [Llama-2-7b-hf-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q5_0.gguf) | Q5_0 | 4.652 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [Llama-2-7b-hf-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q5_K_S.gguf) | Q5_K_S | 4.652 GB | large, low quality loss - recommended | | [Llama-2-7b-hf-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q5_K_M.gguf) | Q5_K_M | 4.783 GB | large, very low quality loss - recommended | | [Llama-2-7b-hf-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q6_K.gguf) | Q6_K | 5.529 GB | very large, extremely low quality loss | | [Llama-2-7b-hf-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-2-7b-hf-GGUF/blob/main/Llama-2-7b-hf-Q8_0.gguf) | Q8_0 | 7.161 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/Llama-2-7b-hf-GGUF --include "Llama-2-7b-hf-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/Llama-2-7b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```