---
license: apache-2.0
language:
- ko
- en
tags:
- moe
---

# **Synatra-Mixtral-8x7B** [(Original Weight)](https://huggingface.co./maywell/Synatra-Mixtral-8x7B)
<img src="./Synatra-Mixtral.png" alt="Synatra-Mixtral-8x7B" width="512"/>


**Synatra-Mixtral-8x7B** is a fine-tuned version of the Mixtral-8x7B-Instruct-v0.1 model using **Korean** datasets.

This model features overwhelmingly superior comprehension and inference capabilities and is licensed under apache-2.0.

# **EXL2 Info**

[measurement.json](./measurement.json)

[8.0bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/8.0bpw), [6.0bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/6.0bpw), [4.0bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/4.0bpw), [3.5bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/3.5bpw), [3.0bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/3.0bpw), [2.6bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/2.6bpw), [2.3bpw](https://huggingface.co./maywell/Synatra-Mixtral-8x7B-exl2/tree/2.3bpw)

<img src="./measurement.png" alt="Measurement" width="512"/>



# **License**
**OPEN**, Apache-2.0.

# **Model Details**

**Base Model**  
[mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co./mistralai/Mixtral-8x7B-Instruct-v0.1)  

**Trained On**  
A100 80GB * 6

**Instruction format**

It follows **Alpaca** format.
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{input}

### Response:
{output}
```

# **Model Benchmark**
TBD

# **Implementation Code**

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-Mixtral-8x7B")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-Mixtral-8x7B")

messages = [
    {"role": "user", "content": "아인슈타인의 상대성이론에 대해서 자세히 설명해줘."},
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```

# **Author's Message**

This model's training got sponsered by no one but support from people around Earth.

[Support Me](https://www.buymeacoffee.com/mwell)

Contact Me on Discord - **is.maywell**

Follow me on twitter: https://twitter.com/stablefluffy