Instructions to use refarde/OPEN-SOLAR-KO-10.7B-S-Core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use refarde/OPEN-SOLAR-KO-10.7B-S-Core with Transformers:

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

pipe = pipeline("text-generation", model="refarde/OPEN-SOLAR-KO-10.7B-S-Core")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("refarde/OPEN-SOLAR-KO-10.7B-S-Core")
model = AutoModelForCausalLM.from_pretrained("refarde/OPEN-SOLAR-KO-10.7B-S-Core", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use refarde/OPEN-SOLAR-KO-10.7B-S-Core with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "refarde/OPEN-SOLAR-KO-10.7B-S-Core"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "refarde/OPEN-SOLAR-KO-10.7B-S-Core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/refarde/OPEN-SOLAR-KO-10.7B-S-Core

SGLang

How to use refarde/OPEN-SOLAR-KO-10.7B-S-Core 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 "refarde/OPEN-SOLAR-KO-10.7B-S-Core" \
    --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": "refarde/OPEN-SOLAR-KO-10.7B-S-Core",
		"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 "refarde/OPEN-SOLAR-KO-10.7B-S-Core" \
        --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": "refarde/OPEN-SOLAR-KO-10.7B-S-Core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use refarde/OPEN-SOLAR-KO-10.7B-S-Core with Docker Model Runner:
```
docker model run hf.co/refarde/OPEN-SOLAR-KO-10.7B-S-Core
```

OPEN-SOLAR-KO-10.7B-S-Core / training_params.json

refarde

Upload folder using huggingface_hub

2bdd0a2 verified over 2 years ago

Raw

History Blame Contribute Delete

1.29 kB

	{
	"model": "beomi/OPEN-SOLAR-KO-10.7B",
	"project_name": "OPEN-SOLAR-KO-10.7B-S-Core",
	"data_path": "royboy0416/ko-alpaca",
	"train_split": "train",
	"valid_split": null,
	"add_eos_token": false,
	"block_size": 1024,
	"model_max_length": 1024,
	"padding": null,
	"trainer": "sft",
	"use_flash_attention_2": false,
	"log": "none",
	"disable_gradient_checkpointing": false,
	"logging_steps": -1,
	"evaluation_strategy": "epoch",
	"save_total_limit": 1,
	"save_strategy": "epoch",
	"auto_find_batch_size": true,
	"mixed_precision": null,
	"lr": 0.0002,
	"epochs": 1,
	"batch_size": 2,
	"warmup_ratio": 0.1,
	"gradient_accumulation": 1,
	"optimizer": "adamw_torch",
	"scheduler": "linear",
	"weight_decay": 0.0,
	"max_grad_norm": 1.0,
	"seed": 42,
	"apply_chat_template": false,
	"quantization": "int4",
	"target_modules": null,
	"merge_adapter": true,
	"peft": true,
	"lora_r": 16,
	"lora_alpha": 32,
	"lora_dropout": 0.05,
	"model_ref": null,
	"dpo_beta": 0.1,
	"prompt_text_column": "prompt",
	"text_column": "text",
	"rejected_text_column": "rejected",
	"push_to_hub": true,
	"repo_id": "refarde/OPEN-SOLAR-KO-10.7B-S-Core",
	"username": "refarde"
	}