Instructions to use HuggingFaceH4/starchat-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/starchat-alpha with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/starchat-alpha")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/starchat-alpha")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/starchat-alpha")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceH4/starchat-alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/starchat-alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/starchat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/starchat-alpha

SGLang

How to use HuggingFaceH4/starchat-alpha 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 "HuggingFaceH4/starchat-alpha" \
    --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": "HuggingFaceH4/starchat-alpha",
		"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 "HuggingFaceH4/starchat-alpha" \
        --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": "HuggingFaceH4/starchat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceH4/starchat-alpha with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/starchat-alpha
```

How to use PEFT+LoRA to fine-tune starchat-alpha

#17

by tonyaw - opened Jun 7, 2023

Discussion

tonyaw

Jun 7, 2023

I want to use PEFT+LoRA to fine-tune starchat-alpha.
I assume "target_modules" shall be set to "starcoder" according to following code:
"utils/other.py"
TRANSFORMERS_MODELS_TO_LORA_TARGET_MODULES_MAPPING = {
"t5": ["q", "v"],
"mt5": ["q", "v"],
"bart": ["q_proj", "v_proj"],
"gpt2": ["c_attn"],
"bloom": ["query_key_value"],
"blip-2": ["q", "v", "q_proj", "v_proj"],
"opt": ["q_proj", "v_proj"],
"gptj": ["q_proj", "v_proj"],
"gpt_neox": ["query_key_value"],
"gpt_neo": ["q_proj", "v_proj"],
"bert": ["query", "value"],
"roberta": ["query", "value"],
"xlm-roberta": ["query", "value"],
"electra": ["query", "value"],
"deberta-v2": ["query_proj", "value_proj"],
"deberta": ["in_proj"],
"layoutlm": ["query", "value"],
"llama": ["q_proj", "v_proj"],
"chatglm": ["query_key_value"],
"starcoder": ["c_attn"]

Then I got the following error:
Unhandled Exception
Traceback (most recent call last):
File "./starcoder_train.py", line 410, in
main()
File "./starcoder_train.py", line 329, in main
model = get_peft_model(model, peft_config)
File "/usr/local/lib/python3.8/dist-packages/peft/mapping.py", line 120, in get_peft_model
return MODEL_TYPE_TO_PEFT_MODEL_MAPPING[peft_config.task_type](model, peft_config)
File "/usr/local/lib/python3.8/dist-packages/peft/peft_model.py", line 691, in init
super().init(model, peft_config, adapter_name)
File "/usr/local/lib/python3.8/dist-packages/peft/peft_model.py", line 100, in init
self.base_model = PEFT_TYPE_TO_MODEL_MAPPING[peft_config.peft_type](
File "/usr/local/lib/python3.8/dist-packages/peft/tuners/lora.py", line 174, in init
self.add_adapter(adapter_name, self.peft_config[adapter_name])
File "/usr/local/lib/python3.8/dist-packages/peft/tuners/lora.py", line 181, in add_adapter
self._find_and_replace(adapter_name)
File "/usr/local/lib/python3.8/dist-packages/peft/tuners/lora.py", line 309, in _find_and_replace
raise ValueError(
ValueError: Target modules starcoder not found in the base model. Please check the target modules and try again.

Looks like it is caused by "weight_map" defined in pytorch_model.bin.index.json. All of them are started with transformer, and doesn't contain "starcoder":
"weight_map": {
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",

Could you please help to check if my usage is right or is it a bug?

tonyaw

Jun 8, 2023

target_modules=['c_attn']

tonyaw changed discussion status to closed Jun 8, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment