Instructions to use MJ199999/gpt3_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MJ199999/gpt3_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MJ199999/gpt3_model")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MJ199999/gpt3_model") model = AutoModelForCausalLM.from_pretrained("MJ199999/gpt3_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MJ199999/gpt3_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MJ199999/gpt3_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MJ199999/gpt3_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MJ199999/gpt3_model
- SGLang
How to use MJ199999/gpt3_model 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 "MJ199999/gpt3_model" \ --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": "MJ199999/gpt3_model", "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 "MJ199999/gpt3_model" \ --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": "MJ199999/gpt3_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MJ199999/gpt3_model with Docker Model Runner:
docker model run hf.co/MJ199999/gpt3_model
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# gpt3_model
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of skt/ko-gpt-trinity-1.2B-v0.5 on
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
- Train Loss: 0.9684
|
| 17 |
- Train Lr: 0.0009999999
|
|
|
|
| 11 |
|
| 12 |
# gpt3_model
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of skt/ko-gpt-trinity-1.2B-v0.5 on korean poem dataset(20C~). When you give an input of any keywords, the model generates the poem that is related to the input keyword. I'm still fine-tuning this model.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
- Train Loss: 0.9684
|
| 17 |
- Train Lr: 0.0009999999
|