README.md

---
language:
- en
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- jiacheng-ye/nl2bash
model-index:
- name: Mistral 7B NL2BASH Agent
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Mistral 7B NL2BASH Agent

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the nl2bash dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5952

## Model description

Mistral 7B NL2BASH Agent is a fine-tuned model that converts natural language queries into Linux commands. It serves as an intelligent agent capable of generating Linux commands based on user input in the form of natural language queries.

## Intended uses & limitations

- Automating the process of creating Linux commands from natural language queries.
- Assisting users in generating complex Linux commands quickly and accurately.
- The model's performance may vary based on the complexity and specificity of the natural language queries.
- It may not handle all edge cases or uncommon scenarios effectively.

## Installation
```bash
pip install transformers accelerate torch bitsandbytes peft  
```

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch 
from peft import PeftModel, PeftConfig

read_token="YOUR HUGGINGFACE TOKEN"

nf4_config = BitsAndBytesConfig(
   load_in_4bit=True,
   bnb_4bit_quant_type="nf4",
   bnb_4bit_use_double_quant=True,
   bnb_4bit_compute_dtype=torch.bfloat16
)

model = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-Instruct-v0.2",
    device_map='auto',
    quantization_config=nf4_config,
    use_cache=False,
    token=read_token
)


model = PeftModel.from_pretrained(model, "pranay-j/mistral-7b-nl2bash-agent",device_map='auto',token=read_token)

tokenizer=AutoTokenizer.from_pretrained("pranay-j/mistral-7b-nl2bash-agent",add_eos_token=False)
nl='Add "execute" to the permissions of all directories in the home directory tree'
prompt= f"[INST] {nl} [/INST]"

inputs=tokenizer(prompt,return_tensors="pt")
input_ids=inputs["input_ids"].to("cuda")

with torch.no_grad():
    out=model.generate(input_ids,top_p=0.5, temperature=0.7, max_new_tokens=30)

tokenizer.decode(out[0][input_ids.shape[-1]:])
# Output: find ~ -type d -exec chmod +x {} </s>
```

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2.5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6136        | 1.0   | 202  | 1.6451          |
| 1.5448        | 2.0   | 404  | 1.5952          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2