Not-For-All-Audiences

Instructions to use nothingiisreal/L3.1-8B-Celeste-V1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nothingiisreal/L3.1-8B-Celeste-V1.5 with Transformers:

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

pipe = pipeline("text-generation", model="nothingiisreal/L3.1-8B-Celeste-V1.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nothingiisreal/L3.1-8B-Celeste-V1.5")
model = AutoModelForCausalLM.from_pretrained("nothingiisreal/L3.1-8B-Celeste-V1.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Local Apps Settings

vLLM

How to use nothingiisreal/L3.1-8B-Celeste-V1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nothingiisreal/L3.1-8B-Celeste-V1.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nothingiisreal/L3.1-8B-Celeste-V1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nothingiisreal/L3.1-8B-Celeste-V1.5

SGLang

How to use nothingiisreal/L3.1-8B-Celeste-V1.5 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 "nothingiisreal/L3.1-8B-Celeste-V1.5" \
    --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": "nothingiisreal/L3.1-8B-Celeste-V1.5",
		"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 "nothingiisreal/L3.1-8B-Celeste-V1.5" \
        --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": "nothingiisreal/L3.1-8B-Celeste-V1.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nothingiisreal/L3.1-8B-Celeste-V1.5 with Docker Model Runner:
```
docker model run hf.co/nothingiisreal/L3.1-8B-Celeste-V1.5
```

L3.1-8B-Celeste-V1.5 / README.md

Commit History

Update README.md

e7ea0e3
verified

aaronday3 commited on Jul 29, 2024

Update README.md

34c0fdd
verified

Auri commited on Jul 29, 2024

Update README.md

ace9728
verified

aaronday3 commited on Jul 28, 2024

Update README.md

a56cdd1
verified

Auri commited on Jul 28, 2024

Update README.md

1a88bbf
verified

Auri commited on Jul 28, 2024

Update README.md

9895ddf
verified

Auri commited on Jul 28, 2024

Update README.md

5380890
verified

aaronday3 commited on Jul 28, 2024

Update README.md

3748e10
verified

Auri commited on Jul 28, 2024

Update README.md

8f15f6e
verified

aaronday3 commited on Jul 28, 2024

Update README.md

84ab3b4
verified

Auri commited on Jul 28, 2024