---
language:
- en
license: llama3
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
base_model: unsloth/llama-3-8b-bnb-4bit
---

### Model Description

- **Developed by:** [Aadarsh Unni Wilson](https://huggingface.co/waadarsh)
- **License:** https://llama.meta.com/llama3/license/
- **Developed by:** waadarsh
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.


### Inference

```python
!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"

from unsloth import FastLanguageModel
import torch
max_seq_length = 2048
dtype = None
load_in_4bit = False
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "waadarsh/llama3-8b-nissan-magnite-16bit",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)

prompt_template_1 = """
You are a helpful assistant for customers of nissan magnite. You are given the following input. Please complete the response in a clear and comprehensive way.
## Question:
{}

## Response:
{}"""
```

```python

FastLanguageModel.for_inference(model)
inputs = tokenizer(
[
    prompt_template_1.format(
        "Tell me about different variants of nissan magnite", #input
        "" # response
    )
], return_tensors = "pt").to("cuda")

with torch.autocast(device_type="cuda"):
    outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.5, repetition_penalty=1.2, use_cache=False)

# Decode the outputs
tokenizer.batch_decode(outputs)

```

```shell
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.
['\nYou are a helpful assistant for customers of nissan magnite. You are given the following input. Please complete the response in a clear and comprehensive way.\n## Question:\nTell me about different variants of nissan magnite\n\n## Response:\nThe Nissan Magnite comes in multiple variants: XE, XL, XV and XV Premium. Each variant has unique features and specifications suited for different needs.<|end_of_text|>']
```

```python

inputs = tokenizer(
[
    prompt_template_1.format(
        "What type of infotainment system is available in the Nissan Magnite?", #input
        "" # response
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)

```

```shell
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.

You are a helpful assistant for customers of nissan magnite. You are given the following input. Please complete the response in a clear and comprehensive way.
## Question:
What type of infotainment system is available in the Nissan Magnite?

## Response:
The Nissan Magnite features an 8-inch touchscreen infotainment system with Android Auto and Apple CarPlay compatibility. It is designed with a user-friendly interface and provides both entertainment and navigation solutions.<|end_of_text|>
```

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)