Instructions to use jojo0217/step3_mk7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jojo0217/step3_mk7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jojo0217/step3_mk7")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jojo0217/step3_mk7") model = AutoModelForCausalLM.from_pretrained("jojo0217/step3_mk7") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jojo0217/step3_mk7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jojo0217/step3_mk7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jojo0217/step3_mk7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jojo0217/step3_mk7
- SGLang
How to use jojo0217/step3_mk7 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 "jojo0217/step3_mk7" \ --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": "jojo0217/step3_mk7", "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 "jojo0217/step3_mk7" \ --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": "jojo0217/step3_mk7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jojo0217/step3_mk7 with Docker Model Runner:
docker model run hf.co/jojo0217/step3_mk7
Create eval/README.md
Browse files- eval/README.md +3 -0
eval/README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ํ๊ฐ ํ์ผ์
๋๋ค. ํ
์คํธ ํ์ผ์ด๊ณ prompt ์์ฑ ๊ธฐ์ค์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค. return_full_text=False, do_sample=False, max_length=512, temperature=1.0, num_beams=1, eos_token_id=2, repetition_penalty=1.1
|
| 2 |
+
|
| 3 |
+
g-eval์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค. payload = { "modelName" : "GOOAI-GPT-00002"(gpt4), "temperature" : "0.5", "topP" : "1.0", "frequencyPenalty" : "0", "presencePenalty" : "0", "user" : "skku-stud", "maxTokens" : "1024", "inputType" : "MIC", "messages" : prompt }
|