Instructions to use Felladrin/Pythia-31M-Chat-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Felladrin/Pythia-31M-Chat-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Felladrin/Pythia-31M-Chat-v1")
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("Felladrin/Pythia-31M-Chat-v1")
model = AutoModelForCausalLM.from_pretrained("Felladrin/Pythia-31M-Chat-v1", 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 Felladrin/Pythia-31M-Chat-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Felladrin/Pythia-31M-Chat-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felladrin/Pythia-31M-Chat-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Felladrin/Pythia-31M-Chat-v1

SGLang

How to use Felladrin/Pythia-31M-Chat-v1 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 "Felladrin/Pythia-31M-Chat-v1" \
    --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": "Felladrin/Pythia-31M-Chat-v1",
		"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 "Felladrin/Pythia-31M-Chat-v1" \
        --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": "Felladrin/Pythia-31M-Chat-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Felladrin/Pythia-31M-Chat-v1 with Docker Model Runner:
```
docker model run hf.co/Felladrin/Pythia-31M-Chat-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A Pythia Chat Model of 31M Parameters

Base model: EleutherAI/pythia-31m
Availability in other ML formats:
- GGUF: Felladrin/gguf-Pythia-31M-Chat-v1
- ONNX: Felladrin/onnx-Pythia-31M-Chat-v1

Recommended prompt format

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant

Recommended inference parameters

penalty_alpha: 0.5
top_k: 2
repetition_penalty: 1.0016

Datasets and parameters used for training

Dataset	License Type
totally-not-an-llm/EverythingLM-data-V3	mit
databricks/databricks-dolly-15k	cc-by-sa-3.0
THUDM/webglm-qa	apache-2.0
starfishmedical/webGPT_x_dolly	cc-by-sa-3.0
Amod/mental_health_counseling_conversations	openrail
sablo/oasst2_curated	apache-2.0
cognitivecomputations/wizard_vicuna_70k_unfiltered	apache-2.0
mlabonne/chatml_dpo_pairs	apache-2.0

SFTTrainer(
    model,
    train_dataset=train_dataset,
    dataset_text_field="text",
    eval_dataset=eval_dataset,
    max_seq_length=2048,
    packing=True,
    args=TrainingArguments(
        learning_rate=2e-6,
        per_device_train_batch_size=1,
        per_device_eval_batch_size=1,
        gradient_accumulation_steps=16,
        lr_scheduler_type="cosine",
        num_train_epochs=1,
        logging_strategy="steps",
        save_strategy="steps",
        evaluation_strategy="steps",
        logging_steps=10,
        eval_steps=10,
        save_steps=10,
        warmup_steps=50,
        load_best_model_at_end=True,
        metric_for_best_model="eval_loss",
        greater_is_better=False,
        weight_decay=0.01,
        save_total_limit=10,
        neftune_noise_alpha=5,
    ),
    callbacks=[
        EarlyStoppingCallback(
            early_stopping_patience=3,
            early_stopping_threshold=0.005
        ),
    ],
)

DPOTrainer(
    model,
    beta=0.1,
    train_dataset=dataset,
    tokenizer=tokenizer,
    eval_dataset=eval_dataset,
    max_length=1536,
    max_prompt_length=1024,
    args=TrainingArguments(
        learning_rate=2e-6,
        per_device_train_batch_size=1,
        per_device_eval_batch_size=1,
        gradient_accumulation_steps=1,
        lr_scheduler_type="cosine",
        num_train_epochs=1,
        logging_strategy="steps",
        save_strategy="steps",
        evaluation_strategy="steps",
        logging_steps=1,
        eval_steps=1,
        save_steps=1,
        warmup_steps=0,
        load_best_model_at_end=True,
        metric_for_best_model="eval_loss",
        greater_is_better=False,
        weight_decay=0.0,
        neftune_noise_alpha=5,
        remove_unused_columns=False,
    ),
    callbacks=[
        EarlyStoppingCallback(
            early_stopping_patience=3,
            early_stopping_threshold=0.005
        ),
    ],
)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.92
AI2 Reasoning Challenge (25-Shot)	22.70
HellaSwag (10-Shot)	25.60
MMLU (5-Shot)	23.24
TruthfulQA (0-shot)	0.00
Winogrande (5-shot)	47.99
GSM8k (5-shot)	0.00