Instructions to use barchetta/test_model_4bit2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barchetta/test_model_4bit2 with Transformers:

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

pipe = pipeline("text-generation", model="barchetta/test_model_4bit2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("barchetta/test_model_4bit2")
model = AutoModelForCausalLM.from_pretrained("barchetta/test_model_4bit2")
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

vLLM

How to use barchetta/test_model_4bit2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barchetta/test_model_4bit2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barchetta/test_model_4bit2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/barchetta/test_model_4bit2

SGLang

How to use barchetta/test_model_4bit2 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 "barchetta/test_model_4bit2" \
    --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": "barchetta/test_model_4bit2",
		"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 "barchetta/test_model_4bit2" \
        --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": "barchetta/test_model_4bit2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use barchetta/test_model_4bit2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for barchetta/test_model_4bit2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for barchetta/test_model_4bit2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for barchetta/test_model_4bit2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="barchetta/test_model_4bit2",
    max_seq_length=2048,
)

Docker Model Runner
How to use barchetta/test_model_4bit2 with Docker Model Runner:
```
docker model run hf.co/barchetta/test_model_4bit2
```

barchetta commited on Apr 9, 2025

Commit

72a6fc1

verified ·

1 Parent(s): f590e04

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

config.json +2 -3
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -43,9 +42,9 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
   "unsloth_fixed": true,
-  "unsloth_version": "2025.3.18",
   "use_cache": true,
   "vocab_size": 128256
 }

 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.3",
   "unsloth_fixed": true,
+  "unsloth_version": "2025.3.19",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.49.0"
 }

   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.50.3"
 }