Instructions to use vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN with Transformers:

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

pipe = pipeline("text-generation", model="vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN

SGLang

How to use vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN 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 "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN" \
    --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": "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN",
		"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 "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN" \
        --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": "vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN with Docker Model Runner:
```
docker model run hf.co/vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN
```

Qwen35-0.8B-FlyFFN-v3-AllFFN

Research artifact from TinyCeNN-LM. Architecture: Qwen3.5-0.8B + FlyFFN-v3 on all 24 FFNs (no dense anchors).

Architecture

Architecture/run type: Qwen3.5-0.8B + FlyFFN-v3 on all 24 FFNs (no dense anchors)
Base model: Qwen/Qwen3.5-0.8B
Dataset: Not recorded
Source code: https://github.com/vtavakkoli/TinyCeNN-LM

Latest saved results

Metric	Value
`num_shards`	8
`mean_route_mix`	0.231608

The Hugging Face repository keeps timestamped run artifacts under runs/. This preserves training reports, configs and run metadata independently of the temporary Colab filesystem.

Saved experiment files

.hf_run_archive/standalone-20260919T081146Z/config.json
.hf_run_archive/standalone-20260919T081146Z/flyffn_config.json
.hf_run_archive/standalone-20260919T081146Z/generation_config.json
.hf_run_archive/standalone-20260919T081146Z/report.json
.hf_run_archive/standalone-20260919T081146Z/tokenizer_config.json
config.json
flyffn_config.json
generation_config.json
report.json
tokenizer_config.json

Reproducibility

Run the matching notebook from the TinyCeNN-LM repository. Colab notebooks use a Hugging Face write token from the HF_TOKEN Colab Secret; tokens should never be pasted into notebook source.

Limitations

This is a research checkpoint. Metrics saved here are the metrics produced by the corresponding training notebook/script; unless explicitly marked as held-out evaluation, they should not be treated as publication-grade benchmark results. Generation quality can differ substantially from the base model.

Citation

If you use this experimental checkpoint, cite the TinyCeNN-LM repository and the upstream base model.

Downloads last month: 660

Model tree for vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(431)

this model