Instructions to use argilla/notus-7b-v1-lora-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use argilla/notus-7b-v1-lora-adapter with Transformers:

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

pipe = pipeline("text-generation", model="argilla/notus-7b-v1-lora-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("argilla/notus-7b-v1-lora-adapter", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use argilla/notus-7b-v1-lora-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "argilla/notus-7b-v1-lora-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "argilla/notus-7b-v1-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/argilla/notus-7b-v1-lora-adapter

SGLang

How to use argilla/notus-7b-v1-lora-adapter 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 "argilla/notus-7b-v1-lora-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "argilla/notus-7b-v1-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "argilla/notus-7b-v1-lora-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "argilla/notus-7b-v1-lora-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use argilla/notus-7b-v1-lora-adapter with Docker Model Runner:
```
docker model run hf.co/argilla/notus-7b-v1-lora-adapter
```

alvarobartt HF Staff commited on Nov 15, 2023

Commit

8fea95e

1 Parent(s): 8a780e9

Upload eval_results.json with huggingface_hub

Browse files

Files changed (1) hide show

eval_results.json +16 -0

eval_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 2.99,
+    "eval_logits/chosen": -3.0396389961242676,
+    "eval_logits/rejected": -3.0144476890563965,
+    "eval_logps/chosen": -298.3731384277344,
+    "eval_logps/rejected": -242.99319458007812,
+    "eval_loss": 0.6432122588157654,
+    "eval_rewards/accuracies": 0.6984127163887024,
+    "eval_rewards/chosen": 0.06627513468265533,
+    "eval_rewards/margins": 0.1006779745221138,
+    "eval_rewards/rejected": -0.034402843564748764,
+    "eval_runtime": 143.4479,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 13.942,
+    "eval_steps_per_second": 0.439
+}