Instructions to use chihoonlee10/T3Q-Merge-SOLAR12 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chihoonlee10/T3Q-Merge-SOLAR12 with Transformers:

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

pipe = pipeline("text-generation", model="chihoonlee10/T3Q-Merge-SOLAR12")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chihoonlee10/T3Q-Merge-SOLAR12")
model = AutoModelForCausalLM.from_pretrained("chihoonlee10/T3Q-Merge-SOLAR12")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chihoonlee10/T3Q-Merge-SOLAR12 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chihoonlee10/T3Q-Merge-SOLAR12"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chihoonlee10/T3Q-Merge-SOLAR12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chihoonlee10/T3Q-Merge-SOLAR12

SGLang

How to use chihoonlee10/T3Q-Merge-SOLAR12 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 "chihoonlee10/T3Q-Merge-SOLAR12" \
    --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": "chihoonlee10/T3Q-Merge-SOLAR12",
		"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 "chihoonlee10/T3Q-Merge-SOLAR12" \
        --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": "chihoonlee10/T3Q-Merge-SOLAR12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chihoonlee10/T3Q-Merge-SOLAR12 with Docker Model Runner:
```
docker model run hf.co/chihoonlee10/T3Q-Merge-SOLAR12
```

chihoonlee10 commited on Mar 14, 2024

Commit

a095ec5

verified ·

1 Parent(s): 15236be

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ license: apache-2.0
 T3Q-Merge-SOLAR12 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
 * [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
-* [hyeogi/SOLAR-10.7B-v1.5](https://huggingface.co/hyeogi/SOLAR-10.7B-v1.5)
 **Model Developers** Chihoon Lee(chlee10), T3Q
@@ -17,7 +17,7 @@ T3Q-Merge-SOLAR12 is a merge of the following models using [mergekit](https://gi
       - sources:
         - model: davidkim205/komt-solar-10.7b-sft-v5
           layer_range: [0, 48]
-        - model: hyeogi/SOLAR-10.7B-v1.5
           layer_range: [0, 48]
   merge_method: slerp

 T3Q-Merge-SOLAR12 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
 * [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
+* [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
 **Model Developers** Chihoon Lee(chlee10), T3Q
       - sources:
         - model: davidkim205/komt-solar-10.7b-sft-v5
           layer_range: [0, 48]
+        - model: LDCC/LDCC-SOLAR-10.7B
           layer_range: [0, 48]
   merge_method: slerp