Instructions to use groxaxo/Qwento-Agentic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use groxaxo/Qwento-Agentic with Transformers:

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

pipe = pipeline("text-generation", model="groxaxo/Qwento-Agentic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("groxaxo/Qwento-Agentic")
model = AutoModelForMultimodalLM.from_pretrained("groxaxo/Qwento-Agentic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use groxaxo/Qwento-Agentic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/groxaxo/Qwento-Agentic

SGLang

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

Docker Model Runner
How to use groxaxo/Qwento-Agentic with Docker Model Runner:
```
docker model run hf.co/groxaxo/Qwento-Agentic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwento-Agentic

⚠️ Test run. This is an early experimental checkpoint, not a finished model.

A QLoRA fine-tune merged into BF16, built on top of Qwen/Qwen-AgentWorld-35B-A3B (a Qwen3.5 MoE: 35B total / ~3B active, hybrid DeltaNet linear-attention + full-attention, 256 experts). It was trained on a curated set of publicly available datasets and is designed for coding tasks.

What this is

Type: test run — a single short curriculum stage (2K sequence length), early checkpoint.
Method: QLoRA (rank 16, α 32) applied to the model's sequence-mixing path (full-attention q/k/v/o + linear-attention input/output projections across all 40 layers), then merged into the BF16 base weights. The 256 MoE experts were left frozen.
Format: BF16 safetensors, drop-in with 🤗 Transformers / vLLM (same architecture and tokenizer as the base).

Training data (curated, publicly available)

A token-balanced blend of cleaned public datasets:

Source	Focus
`Jackrong/Claude-opus-4.7-TraceInversion-5000x`	reasoning / trace-inversion problem solving
`lordx64/reasoning-distill-claude-opus-4-7-max`	high-quality reasoning traces
`lordx64/reasoning-distill-opus-4-7-max-sft`	instruction-style reasoning SFT
`Infatoshi/kernelbench-mega-traces`	GPU-kernel coding traces
`Glint-Research/fable-5-traces`	multi-turn agentic coding (tool use)

All sources were structurally cleaned and quality-filtered before mixing.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained(
    "groxaxo/Qwento-Agentic", torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("groxaxo/Qwento-Agentic")

Limitations

This is a preliminary test checkpoint from a short training run; it has not been benchmarked and should be treated as experimental. It inherits the license and any usage restrictions of the base model (Qwen/Qwen-AgentWorld-35B-A3B).

Downloads last month: 34

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for groxaxo/Qwento-Agentic

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen-AgentWorld-35B-A3B

Finetuned

(5)

this model

Quantizations

1 model