Instructions to use hudsiop/llama32-wikitext2-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hudsiop/llama32-wikitext2-distilled with Transformers:

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

pipe = pipeline("text-generation", model="hudsiop/llama32-wikitext2-distilled")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hudsiop/llama32-wikitext2-distilled")
model = AutoModelForCausalLM.from_pretrained("hudsiop/llama32-wikitext2-distilled", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hudsiop/llama32-wikitext2-distilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hudsiop/llama32-wikitext2-distilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hudsiop/llama32-wikitext2-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hudsiop/llama32-wikitext2-distilled

SGLang

How to use hudsiop/llama32-wikitext2-distilled 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 "hudsiop/llama32-wikitext2-distilled" \
    --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": "hudsiop/llama32-wikitext2-distilled",
		"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 "hudsiop/llama32-wikitext2-distilled" \
        --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": "hudsiop/llama32-wikitext2-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hudsiop/llama32-wikitext2-distilled with Docker Model Runner:
```
docker model run hf.co/hudsiop/llama32-wikitext2-distilled
```

llama32-wikitext2-distilled

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.8552

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
10.1102	0.2619	500	4.9999
9.0742	0.5238	1000	4.5735
8.5261	0.7858	1500	4.3353
7.9589	1.0477	2000	4.2118
7.8108	1.3096	2500	4.1115
7.5611	1.5715	3000	4.0296
7.3756	1.8334	3500	3.9661
6.9172	2.0953	4000	3.9215
6.8475	2.3573	4500	3.8951
6.5798	2.6192	5000	3.8708
6.6206	2.8811	5500	3.8552

Framework versions

Transformers 4.50.3
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 6

Safetensors

Model size

0.4B params

Tensor type

F32