YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
---
license: cc-by-4.0
base_model: chillymiao/Mistral-7B-DSM5
tags:
- gguf
- rocm
- rocmfpx
- amd
- llama.cpp
---
# Mistral-7B-DSM5 - ROCmFPX Quantized
This repository contains AMD ROCmFPX quantized GGUF weights converted from [chillymiao/Mistral-7B-DSM5](https://huggingface.co/chillymiao/Mistral-7B-DSM5) using [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX).
## Available Files
| File | Size | Format |
| --- | --- | --- |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_FAST.gguf | 3.58 GB | Q4_0_ROCMFP4_FAST |
| Mistral-7B-DSM5-Q4_0_ROCMFP4.gguf | 4.39 GB | Q4_0_ROCMFP4 |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_COHERENT.gguf | 3.83 GB | Q4_0_ROCMFP4_COHERENT |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_FAST_COHERENT.gguf | 3.62 GB | Q4_0_ROCMFP4_FAST_COHERENT |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_LEAN.gguf | 3.81 GB | Q4_0_ROCMFP4_LEAN |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_STRIX.gguf | 3.63 GB | Q4_0_ROCMFP4_STRIX |
| Mistral-7B-DSM5-Q4_0_ROCMFP4_STRIX_LEAN.gguf | 3.61 GB | Q4_0_ROCMFP4_STRIX_LEAN |
| Mistral-7B-DSM5-Q2_0_ROCMFPX.gguf | 2.17 GB | Q2_0_ROCMFPX |
| Mistral-7B-DSM5-Q3_0_ROCMFPX.gguf | 3.87 GB | Q3_0_ROCMFPX |
| Mistral-7B-DSM5-Q6_0_ROCMFPX.gguf | 5.57 GB | Q6_0_ROCMFPX |
| Mistral-7B-DSM5-Q8_0_ROCMFPX.gguf | 6.96 GB | Q8_0_ROCMFPX |
| Mistral-7B-DSM5-Q8_0_ROCMFPX_AGENT.gguf | 7.08 GB | Q8_0_ROCMFPX_AGENT |
## Usage Instructions with ROCmFPX llama.cpp
```bash
git clone --depth 1 [https://github.com/charlie12345/ROCmFPX.git](https://github.com/charlie12345/ROCmFPX.git)
cd ROCmFPX
cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=OFF -DGGML_NATIVE=ON
cmake --build build --target llama-cli -j
./build/bin/llama-cli -m Mistral-7B-DSM5-Q4_0_ROCMFP4_FAST.gguf -p "You are a helpful assistant. Hello!" -n 128
```
## License
This model is distributed under the [Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/) license.
- Downloads last month
- 196