Instructions to use littlelearner/littlelearner-5b-chatty with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use littlelearner/littlelearner-5b-chatty with Transformers:

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

pipe = pipeline("text-generation", model="littlelearner/littlelearner-5b-chatty")
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("littlelearner/littlelearner-5b-chatty")
model = AutoModelForCausalLM.from_pretrained("littlelearner/littlelearner-5b-chatty", 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 littlelearner/littlelearner-5b-chatty with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "littlelearner/littlelearner-5b-chatty"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "littlelearner/littlelearner-5b-chatty",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/littlelearner/littlelearner-5b-chatty

SGLang

How to use littlelearner/littlelearner-5b-chatty 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 "littlelearner/littlelearner-5b-chatty" \
    --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": "littlelearner/littlelearner-5b-chatty",
		"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 "littlelearner/littlelearner-5b-chatty" \
        --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": "littlelearner/littlelearner-5b-chatty",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use littlelearner/littlelearner-5b-chatty with Docker Model Runner:
```
docker model run hf.co/littlelearner/littlelearner-5b-chatty
```

Recommended decoding hyperameters

by skowshik - opened 1 day ago

Discussion

skowshik

1 day ago

Hello, what are the recommended decoding hyperparameters (temperature, top-p, top-k) for this suite of models? Especially to reproduce the results of the paper. Thank you!

Jana-Z

Little Learner org about 16 hours ago

Hi!

For the MathCAMPS numbers we use these sampling parameters:

SamplingParams(
n=128,
seed=<0..7>,
temperature=1.0,
top_k=1000,
top_p=1.0,
max_tokens=512,
stop=["<|im_end|>", "<|endoftext|>"],
)
and max_model_len=2048 at vLLM init and no system prompt.

We used n=128 and then evaluated on 8 differently seeded runs to get pass@1024. From these 1024 rollouts, we then estimate the pass@1 numbers via an unbiased pass@k estimator reported in Figure 6.

Jana-Z changed discussion status to closed about 16 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment