Text Generation
Transformers
Safetensors
llama
trl
sft
Generated from Trainer
conversational
text-generation-inference
Instructions to use ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text") model = AutoModelForCausalLM.from_pretrained("ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text
- SGLang
How to use ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text 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 "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text" \ --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": "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text", "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 "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text" \ --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": "ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text with Docker Model Runner:
docker model run hf.co/ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text
Training
- Base Model
- ์์ฒด LLM (solar ๊ธฐ๋ฐ)
- Training dataset
sys_text = """Given the following HTML table, convert it to a descriptive text format.
Summarize the content of the table. and then describe the key features or characteristics of the table."""
table = """WHO์ ICD-11 'Gaming Disorder' ์ง๋ณ์ฝ๋ํ ์๊ธฐ๋ณ ์ถ์ง๊ฒฝ๊ณผ ๋ด์ฉ
<table><tr><td colspan="1" rowspan="1">2014๋
</td><td colspan="1" rowspan="1">ยทWHO ์ ์ ๊ฑด๊ฐ๋ถ ์ค๋
์น์
์๋ฌธ ๊ทธ๋ฃน ํ์์ฒด๋ฅผ ํตํด ๊ฒ์ ๋ฑ ๋์งํธ๋ฏธ๋ ์ด์๊ณผ๋ํ ์ฌ์ฉ์ด ๊ณต์ค๋ณด๊ฑดํ์ ๋ฌธ์ ๋ก ๋์์ด ํ์ํ๋ค๋ ์๊ฒฌ ๋์ถ </td></tr><tr><td colspan="1" rowspan="1">2015๋
</td><td colspan="1" rowspan="1">ยท2์ฐจ TF ํ์ ํตํด Gaming Disorder๋ก ๋ช
๋ช
ํ์ฌ ICD-11 ๋ฑ์ฌ๋ฅผ ์ถ์งํ๊ธฐ๋ก ์ ๋ฌธ๊ฐํฉ์ ๋์ถ </td></tr><tr><td colspan="1" rowspan="1">2016๋
</td><td colspan="1" rowspan="1">ยทICD-11 ๊ฐ์ ์ฌ์ดํธ์ ์ง๋จ๊ธฐ์ค ๊ฒ์ ๋ณด๊ฑด์ ๋ฌธ๊ฐ์ ์๊ฒฌ ์๋ ด ์์ </td></tr><tr><td colspan="1" rowspan="1">2017๋
12์ </td><td colspan="1" rowspan="1">ยทICD-11 ๊ฐ์ ์ ๊ณต๊ฐ </td></tr><tr><td colspan="1" rowspan="1">2018๋
5์ </td><td colspan="1" rowspan="1">ยท71์ฐจ ์ธ๊ณ๋ณด๊ฑด์ดํ์์ ์๊ฑด ์์ ์๊ณ ยท๊ณต๊ฐ๋ ๊ฐ์ ์์ ๋ํ ๊ฐ ํ์๊ตญ์ ๊ฒํ ์๊ฐ ํ๋ณด๋ฅผ ์ํด ICD-11์ฐจ ๊ฐ์ ์ ์์ดํ ์๊ฑด ์์ ์ 1๋
๊ฐ ์ฐ๊ธฐ(2019๋
5์ 72์ฐจ ์ธ๊ณ๋ณด๊ฑด์ดํ) </td></tr><tr><td colspan="1" rowspan="1">2018๋
6์</td><td colspan="1" rowspan="1">ยทICD-11 ์ต์ข
์์ WHO ํํ์ด์ง ๊ฒ์ฌ </td></tr><tr><td colspan="1" rowspan="1">2019๋
5์ </td><td colspan="1" rowspan="1">ยทICD-11 ๊ฐ์ ์ ๋ง์ฅ์ผ์น ํต๊ณผ </td></tr></table>"""
messages = [{'role': 'system', 'content': sys_text}, {'role': 'user', 'content': table}]
output = pipeline(Conversation(messages))
print(output)
- ๊ฒฐ๊ณผ
ํ๋ WHO์ ICD-11 'Gaming Disorder' ์ง๋ณ์ฝ๋ํ ์๊ธฐ๋ณ ์ถ์ง๊ฒฝ๊ณผ ๋ด์ฉ์ ๊ดํ ํ๋ก 7ํ 2์ด์ด๋ฉฐ 2014๋
๋ถํฐ 2019๋
๊น์ง WHO๊ฐ ๊ฒ์ ๋ฑ ๋์งํธ ๋ฏธ๋์ด์ ๊ณผ๋ํ ์ฌ์ฉ์ด ๊ณต์ค๋ณด๊ฑดํ์ ๋ฌธ์ ๋ก ๋์์ด ํ์ํ๋ค๋ ์๊ฒฌ์ ๋์ถํ๊ณ , ์ด๋ฅผ ๋ฐํ์ผ๋ก 'Gaming Disorder'๋ฅผ ๋ช
๋ช
ํ์ฌ ICD-11์ ๋ฑ์ฌํ๊ธฐ๋ก ํฉ์ํ๋ ๊ณผ์ ์ ๋ณด์ฌ์ค๋ค.
1. 2014๋
์ WHO ์ ์ ๊ฑด๊ฐ๋ถ ์ค๋
์น์
์๋ฌธ ๊ทธ๋ฃน ํ์์ฒด์์ ๊ฒ์ ๋ฑ ๋์งํธ ๋ฏธ๋์ด์ ๊ณผ๋ํ ์ฌ์ฉ์ด ๊ณต์ค๋ณด๊ฑดํ์ ๋ฌธ์ ๋ก ๋์์ด ํ์ํ๋ค๋ ์๊ฒฌ์ด ๋์ถ๋์๋ค. 2. 2015๋
์๋ 2์ฐจ TF ํ์๋ฅผ ํตํด 'Gaming Disorder'๋ฅผ ๋ช
๋ช
ํ์ฌ ICD-11์ ๋ฑ์ฌํ๊ธฐ๋ก ์ ๋ฌธ๊ฐ ํฉ์๊ฐ ๋์ถ๋์๋ค. 3. 2019๋
5์์๋ ICD-11 ๊ฐ์ ์์ด ๋ง์ฅ์ผ์น๋ก ํต๊ณผ๋์๋ค.
- Downloads last month
- 10
Model tree for ENERGY-DRINK-LOVE/solar_merge_dpo_table_to_text
Base model
jingyeom/solar_merge_dpo