---
language:
- en
library_name: transformers
license: llama3.1
pipeline_tag: text-generation
---
<!-- Provide a quick summary of what the model is/does. -->

Finetuned Llama 3.1 Instruct model with knowledge distillation  
specifically for expertise on AMD technologies and python coding.

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been  
pushed on the Hub.

- **Developed by:** David Silverstein
- **Language(s) (NLP):** English, Python
- **License:** Free to use under Llama 3.1 licensing terms without warranty
- **Finetuned from model meta-llama/Meta-Llama-3.1-8B-Instruct**

### Model Sources [optional]
<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
Can be used as a development assistant when using AMD technologies and python  
in on-premise environments.

## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and  
limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model:

~~~
import torch  
from transformers import AutoTokenizer, AutoModelForCausalLM  

model_name = 'davidsi/Llama3_1-8B-Instruct-AMD-python'  
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)

messages = [
    {"role": "system", "content": "You are a helpful assistant for AMD technologies and python."},
    {"role": "user", "content": query}
]

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(device)

outputs = model.generate(
    input_ids,
    max_new_tokens=8192,
    eos_token_id=terminators,
    pad_token_id=tokenizer.eos_token_id,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
~~~


## Training Details

Torchtune was used for full finetuning, for 5 epochs on a single Instinct MI210 GPU.  
The training set consisted of 1658 question/answer pairs in Alpaca format.

### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

#### Training Hyperparameters
- **Training regime:** [bf16 non-mixed precision] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data
<!-- This should link to a Dataset Card if possible. -->

### Model Architecture and Objective

This model is a finetuned version of Llama 3.1, which is an auto-regressive language  
model that uses an optimized transformer architecture.