Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- fr
|
| 4 |
+
- it
|
| 5 |
+
- de
|
| 6 |
+
- es
|
| 7 |
+
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
| 10 |
+
inference:
|
| 11 |
+
parameters:
|
| 12 |
+
temperature: 0.5
|
| 13 |
+
widget:
|
| 14 |
+
- messages:
|
| 15 |
+
- role: user
|
| 16 |
+
content: What is your favorite condiment?
|
| 17 |
+
extra_gated_description: If you want to learn more about how we process your personal
|
| 18 |
+
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 19 |
+
tags:
|
| 20 |
+
- llama-cpp
|
| 21 |
+
- gguf
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# Supa-AI/Mixtral-8x7B-Instruct-v0.1-gguf
|
| 25 |
+
This model was converted to GGUF format from [`mistralai/Mixtral-8x7B-Instruct-v0.1`](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) using llama.cpp.
|
| 26 |
+
Refer to the [original model card](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) for more details on the model.
|
| 27 |
+
|
| 28 |
+
## Available Versions
|
| 29 |
+
- `Mixtral-8x7B-Instruct-v0.1.q4_0.gguf` (q4_0)
|
| 30 |
+
- `Mixtral-8x7B-Instruct-v0.1.q4_1.gguf` (q4_1)
|
| 31 |
+
- `Mixtral-8x7B-Instruct-v0.1.q5_0.gguf` (q5_0)
|
| 32 |
+
- `Mixtral-8x7B-Instruct-v0.1.q5_1.gguf` (q5_1)
|
| 33 |
+
- `Mixtral-8x7B-Instruct-v0.1.q8_0.gguf` (q8_0)
|
| 34 |
+
- `Mixtral-8x7B-Instruct-v0.1.q3_k_s.gguf` (q3_K_S)
|
| 35 |
+
- `Mixtral-8x7B-Instruct-v0.1.q3_k_m.gguf` (q3_K_M)
|
| 36 |
+
- `Mixtral-8x7B-Instruct-v0.1.q3_k_l.gguf` (q3_K_L)
|
| 37 |
+
- `Mixtral-8x7B-Instruct-v0.1.q4_k_s.gguf` (q4_K_S)
|
| 38 |
+
- `Mixtral-8x7B-Instruct-v0.1.q4_k_m.gguf` (q4_K_M)
|
| 39 |
+
- `Mixtral-8x7B-Instruct-v0.1.q5_k_s.gguf` (q5_K_S)
|
| 40 |
+
- `Mixtral-8x7B-Instruct-v0.1.q5_k_m.gguf` (q5_K_M)
|
| 41 |
+
- `Mixtral-8x7B-Instruct-v0.1.q6_k.gguf` (q6_K)
|
| 42 |
+
|
| 43 |
+
## Use with llama.cpp
|
| 44 |
+
Replace `FILENAME` with one of the above filenames.
|
| 45 |
+
|
| 46 |
+
### CLI:
|
| 47 |
+
```bash
|
| 48 |
+
llama-cli --hf-repo Supa-AI/Mixtral-8x7B-Instruct-v0.1-gguf --hf-file FILENAME -p "Your prompt here"
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
### Server:
|
| 52 |
+
```bash
|
| 53 |
+
llama-server --hf-repo Supa-AI/Mixtral-8x7B-Instruct-v0.1-gguf --hf-file FILENAME -c 2048
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
## Model Details
|
| 57 |
+
- **Original Model:** [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
|
| 58 |
+
- **Format:** GGUF
|