---
language:
- en
license: apache-2.0
base_model: mistralai/Mixtral-8x7B-v0.1
inference:
  parameters:
    temperature: 0.5
widget:
- messages:
  - role: user
    content: What is your favorite condiment?
---

This model is compressed from the Mixtral-8x7B. Using Low-Rank Approximation, I removed 10 billion parameters from the MLP experts' matrices, enough to run the model on a single A100 80GB GPU using half precision. 


Without being retrained or fine-tuned, the model still retains its core performance:
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62e335bbf15e7fce909fe5d4/IPWpfJfy-nDyxp47HXVzq.png)


# Model Card for minixtral

## Instruction format

This format must be strictly respected, otherwise the model will generate sub-optimal outputs.

The template used to build a prompt for the Instruct model is defined as follows:
```
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
```
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
```python
def tokenize(text):
    return tok.encode(text, add_special_tokens=False)

[BOS_ID] + 
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]
```

In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space. 

In the Transformers library, one can use [chat templates](https://huggingface.co/docs/transformers/main/en/chat_templating) which make sure the right format is applied.

<details>
<summary> Click to expand </summary>

```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")

outputs = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>