Instructions to use wejyy888/Qwen3.5-0.8B-PureText-ZH-EN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wejyy888/Qwen3.5-0.8B-PureText-ZH-EN with Transformers:

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

pipe = pipeline("text-generation", model="wejyy888/Qwen3.5-0.8B-PureText-ZH-EN")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wejyy888/Qwen3.5-0.8B-PureText-ZH-EN")
model = AutoModelForCausalLM.from_pretrained("wejyy888/Qwen3.5-0.8B-PureText-ZH-EN", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wejyy888/Qwen3.5-0.8B-PureText-ZH-EN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wejyy888/Qwen3.5-0.8B-PureText-ZH-EN

SGLang

How to use wejyy888/Qwen3.5-0.8B-PureText-ZH-EN 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 "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN" \
    --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": "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN",
		"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 "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN" \
        --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": "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wejyy888/Qwen3.5-0.8B-PureText-ZH-EN with Docker Model Runner:
```
docker model run hf.co/wejyy888/Qwen3.5-0.8B-PureText-ZH-EN
```

Qwen3.5-0.8B Pure Text ZH-EN

A text-only derivative of Qwen/Qwen3.5-0.8B optimized for Chinese and English inference.

Changes

Converted Qwen3_5ForConditionalGeneration to Qwen3_5ForCausalLM.
Removed the vision tower and MTP weights.
Removed visual, grounding, audio, and TTS special tokens.
Pruned the vocabulary from 248,320 rows to 182,684 real tokens, padded to 182,784 rows for alignment.
Remapped tokenizer IDs and retained old2new.json for converting existing tokenized datasets.
Preserved the original weights exactly for every retained vocabulary item; no additional training was performed.

The resulting checkpoint has 685,284,160 parameters and occupies approximately 1.3 GiB in BF16 safetensors format.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "wejyy888/Qwen3.5-0.8B-PureText-ZH-EN"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto")

messages = [{"role": "user", "content": "介绍一下杭州"}]
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=128)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Use a Transformers version that includes Qwen3_5ForCausalLM support.

Compatibility notes

Previously tokenized datasets must be remapped with old2new.json.
Chinese and English tokenization is preserved exactly after ID remapping.
Other languages still decode correctly through byte fallback, but generally use more tokens.
This checkpoint accepts text only; image, video, audio, and TTS inputs are unsupported.
A short continued-pretraining or SFT stage is recommended before production use to adapt to the reduced vocabulary.

Reproduction

prune_qwen35_zh_en.py contains the conversion procedure. The padded vocabulary rows are initialized to zero so they cannot produce invalid high logits.

Validation

Loaded successfully through AutoModelForCausalLM as Qwen3_5ForCausalLM.
No visual or MTP parameters remain.
Retained-token logits match the source model exactly in the comparison test.
Chinese/English tokenizer equivalence, text chat-template encoding, forward pass, and generation smoke tests pass.

Downloads last month: 154

Safetensors

Model size

0.7B params

Tensor type

BF16

Model tree for wejyy888/Qwen3.5-0.8B-PureText-ZH-EN

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(401)

this model