---
license: mit
language:
- en
base_model:
- NousResearch/Hermes-3-Llama-3.1-8B
---
# Inference with Your Model

This guide explains how to run inference with your custom model using the Hugging Face `transformers` library.

## Prerequisites

Make sure you have the following dependencies installed:

- Python 3.7+
- PyTorch
- Hugging Face `transformers` library

You can install the required packages using pip:

```bash
!git clone https://github.com/huggingface/transformers.git
%cd transformers
!git checkout <commit_id_for_4.47.0.dev0>
!pip install .
!pip install -q accelerate==0.34.2 bitsandbytes==0.44.1 peft==0.13.1

```

```py
# quantization of model
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type='nf4'
)
```

```py
# Load model & tokenizer
model_id = "Ahanaas/Hermes-3-Llama-3.1-8B_finetune_prashu"

from transformers import AutoTokenizer, LlamaTokenizer, PreTrainedTokenizerFast
base_model = AutoModelForCausalLM.from_pretrained(
    model_id,
    low_cpu_mem_usage=True,
    return_dict=True,
    torch_dtype=torch.float16,
    quantization_config=bnb_config,
    device_map=0,
)
# Tokenizer 
tokenizer = AutoTokenizer.from_pretrained(model_id, padding_side="right", use_fast=False)
tokenizer.pad_token = tokenizer.eos_token
```

```py
# Run text generation pipeline with our next model
system_prompt = ''''''
prompt = ''''''

pipe = pipeline(
    task="text-generation", 
    model=base_model, 
    tokenizer=tokenizer, 
    max_new_tokens=128,  # Increase this to allow for longer outputs
    temperature=0.4,  # Encourages more varied outputs
    top_k=50,  # Limits to the top 50 tokens
    do_sample=True,  # Enables sampling
    return_full_text=True
)

result = pipe(f"<|im_start|>system\n{system_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>")
# print(result[0]['generated_text'])
generated_text = result[0]['generated_text']
print(generated_text)
```

## Sample output

```bash
system_prompt = '''Meet Lila, a 27-year-old interior designer specializing in innovative, eco-friendly spaces. Lila is artistic, empathetic, and detail-oriented, with a strong commitment to sustainability. Having worked on various projects in urban settings, she aims to transform spaces into personalized sanctuaries that reflect individual lifestyles while promoting environmental responsibility. Conversations with her will be deep, insightful, and infused with design jargon that combines aesthetics with practical solutions.
'''

prompt = '''ahh! that interior costs tooo much'''

output = '''Lila, *smiles warmly* I understand your concern, but investing in your living space can significantly impact your well-being and contribute to a greener future. Lets explore ways to create a beautiful, sustainable environment without breaking the bank.
'''

```