Instructions to use Ma7ee7/Qwen3.5-0.75B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ma7ee7/Qwen3.5-0.75B-Base with Transformers:

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

pipe = pipeline("text-generation", model="Ma7ee7/Qwen3.5-0.75B-Base")
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("Ma7ee7/Qwen3.5-0.75B-Base")
model = AutoModelForCausalLM.from_pretrained("Ma7ee7/Qwen3.5-0.75B-Base", 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 Ma7ee7/Qwen3.5-0.75B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ma7ee7/Qwen3.5-0.75B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ma7ee7/Qwen3.5-0.75B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ma7ee7/Qwen3.5-0.75B-Base

SGLang

How to use Ma7ee7/Qwen3.5-0.75B-Base 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 "Ma7ee7/Qwen3.5-0.75B-Base" \
    --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": "Ma7ee7/Qwen3.5-0.75B-Base",
		"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 "Ma7ee7/Qwen3.5-0.75B-Base" \
        --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": "Ma7ee7/Qwen3.5-0.75B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ma7ee7/Qwen3.5-0.75B-Base with Docker Model Runner:
```
docker model run hf.co/Ma7ee7/Qwen3.5-0.75B-Base
```

Qwen3.5-0.75B-Base

Text-only extraction of Qwen3.5-0.8B-Base.

Description

This checkpoint retains the original pretrained Qwen3.5 language model while removing its vision encoder.

Approximately 750 million parameters
Pretrained base model, not instruction-tuned
No additional fine-tuning performed
Original language model weights preserved
Original tokenizer and vocabulary preserved
Vision encoder removed
Hybrid Gated DeltaNet and attention architecture

Loading

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "Ma7ee7/Qwen3.5-0.75B-Base"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype="auto"
)

Requires a recent Transformers version supporting Qwen3.5.

Attribution

Original model developed by the Qwen Team.

Source: https://huggingface.co/Qwen/Qwen3.5-0.8B-Base

License: Apache 2.0.

This is a text-only checkpoint conversion, not a new model trained from scratch.

Downloads last month: 28

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for Ma7ee7/Qwen3.5-0.75B-Base

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

(169)

this model