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

Libraries

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

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

pipe = pipeline("text-generation", model="unsloth/Llama-3.2-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Llama-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-1B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

How to use unsloth/Llama-3.2-1B 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 "unsloth/Llama-3.2-1B" \
    --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": "unsloth/Llama-3.2-1B",
		"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 "unsloth/Llama-3.2-1B" \
        --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": "unsloth/Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

danielhanchen commited on Jun 2, 2025

Commit

9535bd9

verified ·

1 Parent(s): 8330ca7

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

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

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -31,7 +30,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.1",
   "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256

 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
   "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.48.1"
 }

   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.52.4"
 }

tokenizer_config.json CHANGED Viewed

@@ -2061,6 +2061,6 @@
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
-}

   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": null
+}