Instructions to use vsan/tiny-pickle-35b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vsan/tiny-pickle-35b with Transformers:

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

pipe = pipeline("text-generation", model="vsan/tiny-pickle-35b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vsan/tiny-pickle-35b")
model = AutoModelForCausalLM.from_pretrained("vsan/tiny-pickle-35b", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vsan/tiny-pickle-35b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vsan/tiny-pickle-35b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vsan/tiny-pickle-35b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vsan/tiny-pickle-35b

SGLang

How to use vsan/tiny-pickle-35b 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 "vsan/tiny-pickle-35b" \
    --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": "vsan/tiny-pickle-35b",
		"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 "vsan/tiny-pickle-35b" \
        --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": "vsan/tiny-pickle-35b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vsan/tiny-pickle-35b with Docker Model Runner:
```
docker model run hf.co/vsan/tiny-pickle-35b
```

tiny-pickle-35b / README.md

vsan

Add files using upload-large-folder tool

53e237d verified 4 days ago

preview code

Raw

History Blame Contribute Delete

566 Bytes

	---
	base_model: Qwen/Qwen3.6-35B-A3B
	pipeline_tag: text-generation
	library_name: transformers
	license: apache-2.0
	datasets:
	- HuggingFaceH4/CodeAlpaca_20K
	tags:
	- qwen
	- moe
	- coding
	- safetensors
	- lora
	---

	# Tiny Pickle

	Tiny Pickle is an experimental short LoRA fine-tune of
	Qwen/Qwen3.6-35B-A3B.

	## Training

	- 1,000 CodeAlpaca examples
	- 20 optimisation steps
	- BF16 LoRA
	- LoRA rank: 16
	- Sequence length: 1,024

	This is a pipeline experiment, not evidence that the model improves upon
	the original base model. It has not undergone comprehensive evaluation.