Instructions to use beomi/Solar-Ko-Recovery-11B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beomi/Solar-Ko-Recovery-11B with Transformers:

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

pipe = pipeline("text-generation", model="beomi/Solar-Ko-Recovery-11B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beomi/Solar-Ko-Recovery-11B")
model = AutoModelForCausalLM.from_pretrained("beomi/Solar-Ko-Recovery-11B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use beomi/Solar-Ko-Recovery-11B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beomi/Solar-Ko-Recovery-11B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beomi/Solar-Ko-Recovery-11B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/beomi/Solar-Ko-Recovery-11B

SGLang

How to use beomi/Solar-Ko-Recovery-11B 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 "beomi/Solar-Ko-Recovery-11B" \
    --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": "beomi/Solar-Ko-Recovery-11B",
		"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 "beomi/Solar-Ko-Recovery-11B" \
        --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": "beomi/Solar-Ko-Recovery-11B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use beomi/Solar-Ko-Recovery-11B with Docker Model Runner:
```
docker model run hf.co/beomi/Solar-Ko-Recovery-11B
```

beomi commited on May 3, 2024

Commit

eb9527e

1 Parent(s): 837f45c

add DPS based tokens

Browse files

Files changed (1) hide show

tokenizer.json +5 -5

tokenizer.json CHANGED Viewed

@@ -64144,11 +64144,11 @@
       "댜": 63987,
       "<|im_start|>": 63988,
       "<|im_end|>": 63989,
-      "<|reserved_0|>": 63990,
-      "<|reserved_1|>": 63991,
-      "<|reserved_2|>": 63992,
-      "<|reserved_3|>": 63993,
-      "<|reserved_4|>": 63994,
       "<|reserved_5|>": 63995,
       "<|reserved_6|>": 63996,
       "<|reserved_7|>": 63997,

       "댜": 63987,
       "<|im_start|>": 63988,
       "<|im_end|>": 63989,
+      "<|sep|>": 63990,
+      "<|endoftext|>": 63991,
+      "<|acc|>": 63992,
+      "<|rrn|>": 63993,
+      "<|tel|>": 63994,
       "<|reserved_5|>": 63995,
       "<|reserved_6|>": 63996,
       "<|reserved_7|>": 63997,