Instructions to use shibatch/tinyqwen35dense2m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shibatch/tinyqwen35dense2m with Transformers:

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

pipe = pipeline("text-generation", model="shibatch/tinyqwen35dense2m")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("shibatch/tinyqwen35dense2m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use shibatch/tinyqwen35dense2m with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shibatch/tinyqwen35dense2m:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shibatch/tinyqwen35dense2m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shibatch/tinyqwen35dense2m:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shibatch/tinyqwen35dense2m:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf shibatch/tinyqwen35dense2m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf shibatch/tinyqwen35dense2m:Q4_K_M

Use Docker

docker model run hf.co/shibatch/tinyqwen35dense2m:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use shibatch/tinyqwen35dense2m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shibatch/tinyqwen35dense2m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shibatch/tinyqwen35dense2m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shibatch/tinyqwen35dense2m:Q4_K_M

SGLang

How to use shibatch/tinyqwen35dense2m 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 "shibatch/tinyqwen35dense2m" \
    --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": "shibatch/tinyqwen35dense2m",
		"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 "shibatch/tinyqwen35dense2m" \
        --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": "shibatch/tinyqwen35dense2m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use shibatch/tinyqwen35dense2m with Ollama:
```
ollama run hf.co/shibatch/tinyqwen35dense2m:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use shibatch/tinyqwen35dense2m with Docker Model Runner:
```
docker model run hf.co/shibatch/tinyqwen35dense2m:Q4_K_M
```

Lemonade

How to use shibatch/tinyqwen35dense2m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shibatch/tinyqwen35dense2m:Q4_K_M

Run and chat with the model

lemonade run user.tinyqwen35dense2m-Q4_K_M

List all available models

lemonade list

Atomic Chat

tinyqwen35dense2m / example_generate.py

shibatch

Upload folder using huggingface_hub

0bd3079 verified about 20 hours ago

Raw History Blame Contribute Delete

1.21 kB

"""Generate a short TinyStories-style continuation from the local HF checkpoint."""

from pathlib import Path

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


def main() -> None:
    model_dir = Path(__file__).resolve().parent / "hf"
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    tokenizer = AutoTokenizer.from_pretrained(model_dir)
    model = AutoModelForCausalLM.from_pretrained(model_dir, dtype=torch.float32).to(device)
    model.eval()
    prompt = "Once upon"
    input_ids = torch.tensor(
        [[tokenizer.bos_token_id] + tokenizer.encode(prompt, add_special_tokens=False)],
        dtype=torch.long,
        device=device,
    )
    torch.manual_seed(1234)
    with torch.no_grad():
        output = model.generate(
            input_ids=input_ids,
            max_new_tokens=100,
            do_sample=True,
            temperature=0.8,
            top_p=0.95,
            top_k=40,
            repetition_penalty=1.1,
            pad_token_id=tokenizer.pad_token_id,
            eos_token_id=tokenizer.eos_token_id,
        )
    print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))


if __name__ == "__main__":
    main()

	"""Generate a short TinyStories-style continuation from the local HF checkpoint."""

	from pathlib import Path

	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer


	def main() -> None:
	model_dir = Path(__file__).resolve().parent / "hf"
	device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
	tokenizer = AutoTokenizer.from_pretrained(model_dir)
	model = AutoModelForCausalLM.from_pretrained(model_dir, dtype=torch.float32).to(device)
	model.eval()
	prompt = "Once upon"
	input_ids = torch.tensor(
	[[tokenizer.bos_token_id] + tokenizer.encode(prompt, add_special_tokens=False)],
	dtype=torch.long,
	device=device,
	)
	torch.manual_seed(1234)
	with torch.no_grad():
	output = model.generate(
	input_ids=input_ids,
	max_new_tokens=100,
	do_sample=True,
	temperature=0.8,
	top_p=0.95,
	top_k=40,
	repetition_penalty=1.1,
	pad_token_id=tokenizer.pad_token_id,
	eos_token_id=tokenizer.eos_token_id,
	)
	print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))


	if __name__ == "__main__":
	main()