Instructions to use rrw-x2/KoSOLAR-10.9B-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rrw-x2/KoSOLAR-10.9B-v0.5 with Transformers:

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

pipe = pipeline("text-generation", model="rrw-x2/KoSOLAR-10.9B-v0.5")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rrw-x2/KoSOLAR-10.9B-v0.5")
model = AutoModelForCausalLM.from_pretrained("rrw-x2/KoSOLAR-10.9B-v0.5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rrw-x2/KoSOLAR-10.9B-v0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rrw-x2/KoSOLAR-10.9B-v0.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rrw-x2/KoSOLAR-10.9B-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rrw-x2/KoSOLAR-10.9B-v0.5

SGLang

How to use rrw-x2/KoSOLAR-10.9B-v0.5 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 "rrw-x2/KoSOLAR-10.9B-v0.5" \
    --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": "rrw-x2/KoSOLAR-10.9B-v0.5",
		"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 "rrw-x2/KoSOLAR-10.9B-v0.5" \
        --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": "rrw-x2/KoSOLAR-10.9B-v0.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rrw-x2/KoSOLAR-10.9B-v0.5 with Docker Model Runner:
```
docker model run hf.co/rrw-x2/KoSOLAR-10.9B-v0.5
```

er1123090 commited on Feb 9, 2024

Commit

9749b8c

verified ·

1 Parent(s): e1a118b

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -10

README.md CHANGED Viewed

@@ -1,19 +1,13 @@
 ---
 license: apache-2.0
----
 language:
-    - ko
-base_model:
-- LDCC/LDCC-SOLAR-10.7B
-- hyeogi/SOLAR-10.7B-dpo-v1
 tags:
-- mergekit
 - merge
-- LDCC/LDCC-SOLAR-10.7B
-- hyeogi/SOLAR-10.7B-dpo-v1
-license: apache-2.0
 ---
 # merge
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

 ---
 license: apache-2.0
+datasets:
+- kyujinpy/KOR-OpenOrca-Platypus-v3
 language:
+- ko
 tags:
 - merge
 ---
 # merge
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).