Instructions to use timorobrecht/full_chinese_gpu3.2-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timorobrecht/full_chinese_gpu3.2-dpo with Transformers:

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

pipe = pipeline("text-generation", model="timorobrecht/full_chinese_gpu3.2-dpo", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("timorobrecht/full_chinese_gpu3.2-dpo", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timorobrecht/full_chinese_gpu3.2-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timorobrecht/full_chinese_gpu3.2-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timorobrecht/full_chinese_gpu3.2-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timorobrecht/full_chinese_gpu3.2-dpo

SGLang

How to use timorobrecht/full_chinese_gpu3.2-dpo 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 "timorobrecht/full_chinese_gpu3.2-dpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timorobrecht/full_chinese_gpu3.2-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "timorobrecht/full_chinese_gpu3.2-dpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timorobrecht/full_chinese_gpu3.2-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use timorobrecht/full_chinese_gpu3.2-dpo with Docker Model Runner:
```
docker model run hf.co/timorobrecht/full_chinese_gpu3.2-dpo
```

full_chinese_gpu3.2-dpo / README.md

timorobrecht

Upload folder using huggingface_hub

eea02cb verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.13 kB

	---
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- causal-lm
	- trust-remote-code
	- sentencepiece
	---

	# Pinyin-Code Causal LM

	This repository contains a custom Transformers causal language model.
	External evaluation repositories should load it with
	`trust_remote_code=True` and use the `causal` backend.

	## Dependencies

	Install the runtime dependencies before loading the model:

	```bash
	pip install torch transformers safetensors sentencepiece pypinyin jieba
	```

	`sentencepiece` is required for `AutoTokenizer`. `pypinyin` is required
	for raw Mandarin-to-pinyin tokenization. `jieba` is required when
	`use_jieba` is true; this export was created with `use_jieba=true`.

	## Loading

	```python
	from transformers import AutoConfig, AutoModel, AutoModelForCausalLM, AutoTokenizer

	model_path = "PATH_OR_REPO_ID"

	config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
	tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
	base_model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
	```

	## Evaluation

	Configure external evaluators with:

	- model path: this local folder or Hugging Face repo ID
	- backend: `causal`
	- trust remote code: enabled

	The tokenizer accepts raw text through standard calls such as
	`tokenizer(text)`, `tokenizer(text, add_special_tokens=False)`, and
	`tokenizer(texts, padding=True, truncation=True, return_tensors="pt")`.
	It also accepts `return_offsets_mapping=True` for compatibility with
	completion-ranking evaluators that need suffix masks. The model supports
	`output_hidden_states=True` for representation extraction tasks.

	This export sets `patch_pathlib_utf8_open=true` in `config.json`.
	When loaded with `trust_remote_code=True`, the config installs a narrow
	Windows compatibility shim so later text-mode `Path.open("r")` calls
	without an explicit encoding default to UTF-8. Set
	`PINYIN_CODE_DISABLE_UTF8_OPEN_PATCH=1` before loading the model to
	disable that shim.

	Export metadata:

	- transliteration: `pinyin-code`
	- use_jieba: `true`