---
license: mit
datasets:
- guanaco/guanaco_clean
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6324ce4d5d0cf5c62c6e3c5a/8Z0UpwJzji2G_HVh75uDT.png)

# Model Details
**Model Name:** thesven/Phi3-mini-128k-guanaco                                       
**Base Model:** [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)  
**Fine-tuning Method:** Supervised Fine-Tuning (SFT)  
**Dataset:** [Guanaco Clean](https://huggingface.co/datasets/guanaco/guanaco_clean)  
**Training Data:** A subset of filtered chats from the Guanaco dataset where the total input length was equal or less than 512 tokens.                
**Training Duration:** 8 hours  
**Hardware:** Nvidia RTX A4500  
**Epochs:** 3

## Training Procedure
This model was finetuned on chat sequences to improve it's overall chat performance.


### Intended Use
This model is designed to improve instruction-following capabilities, particularly for code-related tasks.

## Getting Started
### Instruct Template
<|system|>
{system_message} <|end|>
<|user|>
{Prompt) <|end|>
<|assistant|>

### Transfromers
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

model_name_or_path = "thesven/Phi3-mini-128k-guanaco"

# BitsAndBytesConfig for loading the model in 4-bit precision
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype="float16",
)

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path,
    device_map="auto",
    trust_remote_code=False,
    revision="main",
    quantization_config=bnb_config
)
model.pad_token = model.config.eos_token_id

prompt_template = '''
<|system|>
You are an expert developer. Please help me with any coding questions.<|end|>
<|user|>
Create a function to get the total sum from an array of ints.<|end|>
<|assistant|>
'''

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.1, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=256)

generated_text = tokenizer.decode(output[0, len(input_ids[0]):], skip_special_tokens=True)
print(generated_text)
```