Instructions to use 4stack/gpt-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 4stack/gpt-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="4stack/gpt-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("4stack/gpt-finetuned")
model = AutoModelForCausalLM.from_pretrained("4stack/gpt-finetuned")
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 4stack/gpt-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "4stack/gpt-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "4stack/gpt-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/4stack/gpt-finetuned

SGLang

How to use 4stack/gpt-finetuned 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 "4stack/gpt-finetuned" \
    --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": "4stack/gpt-finetuned",
		"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 "4stack/gpt-finetuned" \
        --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": "4stack/gpt-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 4stack/gpt-finetuned with Docker Model Runner:
```
docker model run hf.co/4stack/gpt-finetuned
```

4stack commited on Oct 6, 2024

Commit

cb99726

verified ·

1 Parent(s): 28cc7f6

End of training

Browse files

Files changed (2) hide show

tokenizer_config.json +1 -0
training_args.bin +1 -1

tokenizer_config.json CHANGED Viewed

@@ -9,6 +9,7 @@
       "special": true
     }
   },
   "clean_up_tokenization_spaces": false,
   "model_max_length": 512,
   "tokenizer_class": "OpenAIGPTTokenizer",

       "special": true
     }
   },
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "model_max_length": 512,
   "tokenizer_class": "OpenAIGPTTokenizer",

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032925071306e004d21b9a91b39e8ac02deaad91985859078d14349a97c745cc
 size 5240

 version https://git-lfs.github.com/spec/v1
+oid sha256:97fca82887800e97268bef24a035c96cdc5bff82292f39a8e0a03993f61e3e6b
 size 5240