Instructions to use yanolja/KoSOLAR-10.7B-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yanolja/KoSOLAR-10.7B-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="yanolja/KoSOLAR-10.7B-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yanolja/KoSOLAR-10.7B-v0.2")
model = AutoModelForCausalLM.from_pretrained("yanolja/KoSOLAR-10.7B-v0.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yanolja/KoSOLAR-10.7B-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yanolja/KoSOLAR-10.7B-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yanolja/KoSOLAR-10.7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yanolja/KoSOLAR-10.7B-v0.2

SGLang

How to use yanolja/KoSOLAR-10.7B-v0.2 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 "yanolja/KoSOLAR-10.7B-v0.2" \
    --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": "yanolja/KoSOLAR-10.7B-v0.2",
		"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 "yanolja/KoSOLAR-10.7B-v0.2" \
        --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": "yanolja/KoSOLAR-10.7B-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yanolja/KoSOLAR-10.7B-v0.2 with Docker Model Runner:
```
docker model run hf.co/yanolja/KoSOLAR-10.7B-v0.2
```

seungduk commited on Jan 18, 2024

Commit

bb1f1dd

1 Parent(s): 1656bee

Update license

Browse files

Files changed (2) hide show

README.md +3 -1
config.json +1 -1

README.md CHANGED Viewed

@@ -1,8 +1,10 @@
 ---
 tags:
 - generated_from_trainer
 model-index:
-- name: upstage/SOLAR-10.7B-v1.0
   results: []
 ---
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

 ---
+license: apache-2.0
+base_model: upstage/SOLAR-10.7B-v1.0
 tags:
 - generated_from_trainer
 model-index:
+- name: yanolja/KoSOLAR-10.7B-v0.2
   results: []
 ---
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/data/shared/KoSOLAR-10.7B-v0.2-stage9",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "yanolja/KoSOLAR-10.7B-v0.2",
   "architectures": [
     "LlamaForCausalLM"
   ],