Instructions to use wassname/qwen3.5-8lyr-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wassname/qwen3.5-8lyr-tiny-random with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wassname/qwen3.5-8lyr-tiny-random") 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("wassname/qwen3.5-8lyr-tiny-random") model = AutoModelForCausalLM.from_pretrained("wassname/qwen3.5-8lyr-tiny-random", 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 wassname/qwen3.5-8lyr-tiny-random with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wassname/qwen3.5-8lyr-tiny-random" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wassname/qwen3.5-8lyr-tiny-random", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wassname/qwen3.5-8lyr-tiny-random
- SGLang
How to use wassname/qwen3.5-8lyr-tiny-random 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 "wassname/qwen3.5-8lyr-tiny-random" \ --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": "wassname/qwen3.5-8lyr-tiny-random", "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 "wassname/qwen3.5-8lyr-tiny-random" \ --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": "wassname/qwen3.5-8lyr-tiny-random", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wassname/qwen3.5-8lyr-tiny-random with Docker Model Runner:
docker model run hf.co/wassname/qwen3.5-8lyr-tiny-random
Qwen3.5 8-layer tiny random chat checkpoint
Random weights for software tests, not a trained assistant. Text only; no image/audio/video support. Original Qwen3.5-4B tokenizer, full vocabulary, chat/thinking/tool template and special tokens. Width 64, MLP 128, 8 layers, 16,227,664 parameters, bf16 safetensors with tied embeddings. Keeps Qwen3.5's three linear-attention layers followed by one full-attention layer. RoPE sections are resized to [2, 1, 1] for head dimension 32 and rotary fraction 0.25. CPU operation needs no FlashAttention or FLA installation; optimized GPU kernels are optional.
from transformers import AutoModelForCausalLM, AutoTokenizer
path = "wassname/qwen3.5-8lyr-tiny-random"
tok = AutoTokenizer.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(path, attn_implementation="eager")
inputs = tok.apply_chat_template(
[{"role": "user", "content": "Hello!"}],
add_generation_prompt=True, enable_thinking=False,
return_tensors="pt", return_dict=True,
)
reply = model.generate(**inputs, max_new_tokens=8, do_sample=False)
For attention weights, load with attn_implementation="eager" and pass output_attentions=True.
Only full-attention layers return maps; linear-attention layers use recurrent states, not attention maps.
For eight layers the returned maps correspond to zero-based layers 3 and 7, not all eight layers.
SDPA supports generation but does not return these maps in the tested Transformers version.
Built from Qwen/Qwen3.5-4B@851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a with seed 42; no pretrained weights copied.
Build: uv run python -m lucid3.tiny_qwen --out <new-directory> --layers 8 --seed 42.
Source tokenizer/config/LICENSE must be cached locally. See build.json and verification.json.
Checked saved-model forward/backward, cached decoding, padded batches, generation and template preservation.
Use --layers 32 for LUCID tests that access layers 16 and 30. Eight layers cannot supply those layers.
Random outputs are meaningless; successful generation does not establish chat or tool-use ability.
- Downloads last month
- 27