Instructions to use akhauriyash/Llama-3.2-1B-Butler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akhauriyash/Llama-3.2-1B-Butler with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="akhauriyash/Llama-3.2-1B-Butler", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("akhauriyash/Llama-3.2-1B-Butler", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use akhauriyash/Llama-3.2-1B-Butler with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "akhauriyash/Llama-3.2-1B-Butler"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akhauriyash/Llama-3.2-1B-Butler",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/akhauriyash/Llama-3.2-1B-Butler

SGLang

How to use akhauriyash/Llama-3.2-1B-Butler with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "akhauriyash/Llama-3.2-1B-Butler" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akhauriyash/Llama-3.2-1B-Butler",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "akhauriyash/Llama-3.2-1B-Butler" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "akhauriyash/Llama-3.2-1B-Butler",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use akhauriyash/Llama-3.2-1B-Butler with Docker Model Runner:
```
docker model run hf.co/akhauriyash/Llama-3.2-1B-Butler
```

TokenButler

The collection of TokenButler models can be found here. To run the meta-llama/Llama-3.2-1B model, follow:

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

question = "If millionaires have butlers, why don't million dollar language models have a butler too? I think its because "

model_name = "akhauriyash/Llama-3.2-1B-Butler"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)

generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
response = generator(question, max_new_tokens=200, do_sample=True, top_p=0.95, temperature=0.7)

print(response[0]['generated_text'][len(question):])

Note that the 'default' configured sparsity is 50%. Further, there is a 'sliding window' of 128 and 8 'anchor tokens'. To 'change' the sparsity, you can use the following function after loading the model. Please note that the 'fixed' is the only supported strategy at the moment, which 'fixes' the sparsity of each layer (except the first) at the 'pc' (percentage) mentioned. This can also be found at test_hf.py. Sliding window and anchor tokens can be changed in a similar manner.

def set_sparsity(model, sparsity):
    for module in model.modules():
        if module.__class__.__name__.__contains__("AttentionExperimental"):
            module.token_sparse_method = sparsity
            module.set_token_sparsity()
    return model

model = set_sparsity(model, "fixed_60pc")