Instructions to use wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld with Transformers:

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

pipe = pipeline("text-generation", model="wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld")
model = AutoModelForCausalLM.from_pretrained("wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld", 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 wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld

SGLang

How to use wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld 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 "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld" \
    --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": "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld",
		"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 "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld" \
        --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": "wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld with Docker Model Runner:
```
docker model run hf.co/wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Llama-3.2-3B-Instruct-SFT-ScienceWorld

PRIVATE — internal research checkpoint. Do not redistribute.


Task	ScienceWorld
Stage	SFT (behavior-cloning) initialization
Base	`meta-llama/Llama-3.2-3B-Instruct` (Built with Llama)
Init for this run	`models/llama-3.2-3b-instruct`
Source checkpoint	`rl/ckpts/sw_sft_llama3.2-3b/global_step_198` (global_step 198)
Format	bf16 safetensors, merged from hf-dir -> bf16 cast
Params	3,212,749,824
Weight drift vs. init (mean rel-L2)	4.69e-03 (max 9.40e-03, 226 / 255 tensors changed)
Reload bit-exact check	True

Optimizer state is not included (inference/eval only; the fp32 FSDP shards stay on HiPerGator /blue). Load with AutoModelForCausalLM.from_pretrained(..., torch_dtype=torch.bfloat16) or vLLM; the chat template is the stock Llama-3 template shipped in chat_template.jinja.

Licensed under the Llama 3.2 Community License; derivative of Meta Llama.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for wayne377/Llama-3.2-3B-Instruct-SFT-ScienceWorld

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(2016)

this model