Instructions to use openchat/openchat_3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openchat/openchat_3.5 with Transformers:

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

pipe = pipeline("text-generation", model="openchat/openchat_3.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_3.5")
model = AutoModelForCausalLM.from_pretrained("openchat/openchat_3.5")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openchat/openchat_3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openchat/openchat_3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openchat/openchat_3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openchat/openchat_3.5

SGLang

How to use openchat/openchat_3.5 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 "openchat/openchat_3.5" \
    --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": "openchat/openchat_3.5",
		"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 "openchat/openchat_3.5" \
        --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": "openchat/openchat_3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openchat/openchat_3.5 with Docker Model Runner:
```
docker model run hf.co/openchat/openchat_3.5
```

What is the best way for the inference process in LORA in PEFT approach

#43

by Pradeep1995 - opened Dec 29, 2023

Discussion

Pradeep1995

Dec 29, 2023

Here is the SFTtrainer method i used for finetuning mistral

trainer = SFTTrainer(
    model=peft_model,
    train_dataset=data,
    peft_config=peft_config,
    dataset_text_field=" column name",
    max_seq_length=3000,
    tokenizer=tokenizer,
    args=training_arguments,
    packing=packing,
)
trainer.train()

I found different mechanisms for the finetuned model inference after PEFT based LORA finetuning

Method - 1

save adapter after completing training and then merge with base model then use for inference

trainer.model.save_pretrained("new_adapter_path")
from peft import PeftModel
finetuned_model = PeftModel.from_pretrained(base_model,
                                  new_adapter_path,
                                  torch_dtype=torch.float16,
                                  is_trainable=False,
                                  device_map="auto"
                                  )
finetuned_model = finetuned_model.merge_and_unload()

Method - 2

save checkpoints during training and then use the checkpoint with the least loss

from peft import PeftModel
finetuned_model = PeftModel.from_pretrained(base_model,
                                  "least loss checkpoint path",
                                  torch_dtype=torch.float16,
                                  is_trainable=False,
                                  device_map="auto"
                                  )
finetuned_model = finetuned_model.merge_and_unload()

Method - 3

same method with AutoPeftModelForCausalLM class

model = AutoPeftModelForCausalLM.from_pretrained(
    "output directory checkpoint path",
    low_cpu_mem_usage=True,
    return_dict=True,
    torch_dtype=torch.float16,
    device_map="cuda")
finetuned_model = finetuned_model.merge_and_unload()

Method-4

AutoPeftModelForCausalLM class specifies the output folder without specifying a specific checkpoint

instruction_tuned_model = AutoPeftModelForCausalLM.from_pretrained(
    training_args.output_dir,
    torch_dtype=torch.bfloat16,
    device_map = 'auto',
    trust_remote_code=True,
)
finetuned_model = finetuned_model.merge_and_unload()

Method-5
All the above methods without merging

#finetuned_model = finetuned_model.merge_and_unload()

Which is the actual method I should follow for inference?
and when to use which method over another?

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