Instructions to use tjcrims0n/q36 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tjcrims0n/q36 with Transformers:

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

pipe = pipeline("text-generation", model="tjcrims0n/q36")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tjcrims0n/q36")
model = AutoModelForCausalLM.from_pretrained("tjcrims0n/q36")
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 tjcrims0n/q36 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tjcrims0n/q36"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tjcrims0n/q36",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tjcrims0n/q36

SGLang

How to use tjcrims0n/q36 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 "tjcrims0n/q36" \
    --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": "tjcrims0n/q36",
		"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 "tjcrims0n/q36" \
        --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": "tjcrims0n/q36",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tjcrims0n/q36 with Docker Model Runner:
```
docker model run hf.co/tjcrims0n/q36
```

q36

Merged full-model export from khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled using Annihilate trial 71.

Export

Trial: 71
Refusals: 0 / 6
KL divergence: 0.005478133447468281
Export dtype: bfloat16
Method: Annihilate LoRA trial merged into the base model and saved as a full Transformers safetensors model.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("tjcrims0n/q36", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("tjcrims0n/q36")

messages = [{"role": "user", "content": "Hello"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=120)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 38

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for tjcrims0n/q36

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

unsloth/Qwen3-4B-Thinking-2507

Finetuned

khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled

Finetuned

(1)

this model