Instructions to use v000000/NM-12B-Lyris-dev-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use v000000/NM-12B-Lyris-dev-3 with Transformers:

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

pipe = pipeline("text-generation", model="v000000/NM-12B-Lyris-dev-3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("v000000/NM-12B-Lyris-dev-3")
model = AutoModelForCausalLM.from_pretrained("v000000/NM-12B-Lyris-dev-3")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use v000000/NM-12B-Lyris-dev-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v000000/NM-12B-Lyris-dev-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/NM-12B-Lyris-dev-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/v000000/NM-12B-Lyris-dev-3

SGLang

How to use v000000/NM-12B-Lyris-dev-3 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 "v000000/NM-12B-Lyris-dev-3" \
    --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": "v000000/NM-12B-Lyris-dev-3",
		"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 "v000000/NM-12B-Lyris-dev-3" \
        --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": "v000000/NM-12B-Lyris-dev-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use v000000/NM-12B-Lyris-dev-3 with Docker Model Runner:
```
docker model run hf.co/v000000/NM-12B-Lyris-dev-3
```

v000000 commited on Sep 5, 2024

Commit

f496196

verified ·

1 Parent(s): a300552

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -10,8 +10,10 @@ tags:
 ---
 Lyris-dev3-Mistral-Nemo-12B-2407
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/FykxidAsKvgxipFa7ZIaC.png)
 *EXPERIMENTAL*
 attempt to fix Sao10k's Lyra-V3 prompt format and stop token >and boost smarts. with strategic *LATCOS* vector similarity merging

 ---
 Lyris-dev3-Mistral-Nemo-12B-2407
+------------------------------------------------------------------
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/FykxidAsKvgxipFa7ZIaC.png)
 *EXPERIMENTAL*
 attempt to fix Sao10k's Lyra-V3 prompt format and stop token >and boost smarts. with strategic *LATCOS* vector similarity merging