Instructions to use bluuwhale/L3-SAO-MIX-8B-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bluuwhale/L3-SAO-MIX-8B-V1 with Transformers:

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

pipe = pipeline("text-generation", model="bluuwhale/L3-SAO-MIX-8B-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bluuwhale/L3-SAO-MIX-8B-V1")
model = AutoModelForCausalLM.from_pretrained("bluuwhale/L3-SAO-MIX-8B-V1", device_map="auto")
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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bluuwhale/L3-SAO-MIX-8B-V1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bluuwhale/L3-SAO-MIX-8B-V1

SGLang

How to use bluuwhale/L3-SAO-MIX-8B-V1 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 "bluuwhale/L3-SAO-MIX-8B-V1" \
    --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": "bluuwhale/L3-SAO-MIX-8B-V1",
		"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 "bluuwhale/L3-SAO-MIX-8B-V1" \
        --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": "bluuwhale/L3-SAO-MIX-8B-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bluuwhale/L3-SAO-MIX-8B-V1 with Docker Model Runner:
```
docker model run hf.co/bluuwhale/L3-SAO-MIX-8B-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Experimental merge of Sao10k Llama3-8B based model

L3-SAO-MIX-8B-V1

This is a merge of pre-trained language models created using mergekit.

I'm trying to combine the best model from Sao10k. And turn out, this is beyond my expectation. I use it for RP and ERP on scenario card. And it follow the instruction very well (At least for me). All credits and thanks go to Sao10k for providing amazing models used in the merge.

Prompt template: Llama3 Instruct.

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Settings

Temprature: 1.3
Min-P: 0.1
// If using DRY
Multiplier: 2
Base: 1.75
Allowed Length: 2
Penalty Range: 0

Merge details

Merge Method

This model was merged using the della merge method using Sao10K/L3-8B-Niitama-v1 as a base.

Models Merged

The following models were included in the merge:

Sao10K/L3-8B-Lunaris-v1
Sao10K/L3-8B-Stheno-v3.2
Sao10K/L3-8B-Niitama-v1
Sao10K/L3-8B-Tamamo-v1

Configuration

The following YAML configuration was used to produce this model:

base_model: Sao10K/L3-8B-Niitama-v1
merge_method: della
dtype: bfloat16
models:
  - model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Niitama-v1
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Tamamo-v1
    parameters:
      weight: 1.0