Instructions to use er1123090/T3Q_SOLAR_SLERP_v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use er1123090/T3Q_SOLAR_SLERP_v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="er1123090/T3Q_SOLAR_SLERP_v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("er1123090/T3Q_SOLAR_SLERP_v1.0")
model = AutoModelForCausalLM.from_pretrained("er1123090/T3Q_SOLAR_SLERP_v1.0")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use er1123090/T3Q_SOLAR_SLERP_v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "er1123090/T3Q_SOLAR_SLERP_v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "er1123090/T3Q_SOLAR_SLERP_v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/er1123090/T3Q_SOLAR_SLERP_v1.0

SGLang

How to use er1123090/T3Q_SOLAR_SLERP_v1.0 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 "er1123090/T3Q_SOLAR_SLERP_v1.0" \
    --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": "er1123090/T3Q_SOLAR_SLERP_v1.0",
		"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 "er1123090/T3Q_SOLAR_SLERP_v1.0" \
        --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": "er1123090/T3Q_SOLAR_SLERP_v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use er1123090/T3Q_SOLAR_SLERP_v1.0 with Docker Model Runner:
```
docker model run hf.co/er1123090/T3Q_SOLAR_SLERP_v1.0
```

T3Q_SOLAR_SLERP_v1.0 / mergekit_config.yml

er1123090

Upload folder using huggingface_hub

8140e03 verified about 2 years ago

Raw

History Blame Contribute Delete

555 Bytes

	slices:
	- sources:
	- model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
	layer_range: [0, 48]
	- model: hwkwon/S-SOLAR-10.7B-v1.5
	layer_range: [0, 48]
	# or, the equivalent models: syntax:
	# models:
	# - model: psmathur/orca_mini_v3_13b
	# - model: garage-bAInd/Platypus2-13B
	merge_method: slerp
	base_model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
	parameters:
	t:
	- filter: self_attn
	value: [0, 0.5, 0.3, 0.7, 1]
	- filter: mlp
	value: [1, 0.5, 0.7, 0.3, 0]
	- value: 0.5 # fallback for rest of tensors
	dtype: float16