Instructions to use kurogane/tinystorys_llama_vocab768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kurogane/tinystorys_llama_vocab768 with Transformers:

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

pipe = pipeline("text-generation", model="kurogane/tinystorys_llama_vocab768")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kurogane/tinystorys_llama_vocab768")
model = AutoModelForCausalLM.from_pretrained("kurogane/tinystorys_llama_vocab768", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kurogane/tinystorys_llama_vocab768 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kurogane/tinystorys_llama_vocab768"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kurogane/tinystorys_llama_vocab768",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kurogane/tinystorys_llama_vocab768

SGLang

How to use kurogane/tinystorys_llama_vocab768 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 "kurogane/tinystorys_llama_vocab768" \
    --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": "kurogane/tinystorys_llama_vocab768",
		"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 "kurogane/tinystorys_llama_vocab768" \
        --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": "kurogane/tinystorys_llama_vocab768",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kurogane/tinystorys_llama_vocab768 with Docker Model Runner:
```
docker model run hf.co/kurogane/tinystorys_llama_vocab768
```

Model Card for tiny_llama_768

This model is a fine-tuned version of . It has been trained using TRL.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig


model_id = "kurogane/tinystorys_llama_vocab768"
cache_dir = r"/media/kurogane/backup/cache"

model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", cache_dir=cache_dir)
tokenizer = AutoTokenizer.from_pretrained(model_id, padding_side="left", cache_dir=cache_dir)

model_inputs = tokenizer(["A list of colors: red, blue"], return_tensors="pt").to(model.device)
generated_ids = model.generate(**model_inputs)

s_output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(s_output)

result example

A list of colors: red, blue, yellow, green, orange. All the people

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.24.0
Transformers: 5.8.0
Pytorch: 2.11.0+cu129
Datasets: 4.3.0
Tokenizers: 0.22.2

Used dataset

roneneldan/TinyStories at 5,000 steps

Downloads last month: 5

Safetensors

Model size

5.31M params

Tensor type

F32

Dataset used to train kurogane/tinystorys_llama_vocab768

Collection including kurogane/tinystorys_llama_vocab768

Multiscreen Models

Collection

4 items • Updated May 20