Instructions to use thesven/Phi-nut-Butter-Codebagel-v1-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thesven/Phi-nut-Butter-Codebagel-v1-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="thesven/Phi-nut-Butter-Codebagel-v1-GPTQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thesven/Phi-nut-Butter-Codebagel-v1-GPTQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("thesven/Phi-nut-Butter-Codebagel-v1-GPTQ", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thesven/Phi-nut-Butter-Codebagel-v1-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thesven/Phi-nut-Butter-Codebagel-v1-GPTQ

SGLang

How to use thesven/Phi-nut-Butter-Codebagel-v1-GPTQ 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 "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thesven/Phi-nut-Butter-Codebagel-v1-GPTQ with Docker Model Runner:
```
docker model run hf.co/thesven/Phi-nut-Butter-Codebagel-v1-GPTQ
```

Phi-nut-Butter-Codebagel-v1

Model Details

Model Name: Phi-nut-Butter-Codebagel-v1 Quantization Data: 4bit GPTQ

Quantization Details

This is a GPTQ 4 bit quantization of thesven/Phi-nut-Butter-Codebagel-v1. For more details on the model please see the model card.

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

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name_or_path = "thesven/Phi-nut-Butter-Codebagel-v1-GPTQ"

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",
)
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|>
In typescript how would I use a function that looks like this <T>(config:T):T<|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)
display(generated_text)

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

I32

F16

Dataset used to train thesven/Phi-nut-Butter-Codebagel-v1-GPTQ

Collection including thesven/Phi-nut-Butter-Codebagel-v1-GPTQ

GPTQ Quants

Collection

15 items • Updated Sep 13, 2024