Instructions to use Yobenboben/L3.3-Smog-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yobenboben/L3.3-Smog-70B with Transformers:

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

pipe = pipeline("text-generation", model="Yobenboben/L3.3-Smog-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yobenboben/L3.3-Smog-70B")
model = AutoModelForCausalLM.from_pretrained("Yobenboben/L3.3-Smog-70B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yobenboben/L3.3-Smog-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yobenboben/L3.3-Smog-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yobenboben/L3.3-Smog-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yobenboben/L3.3-Smog-70B

SGLang

How to use Yobenboben/L3.3-Smog-70B 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 "Yobenboben/L3.3-Smog-70B" \
    --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": "Yobenboben/L3.3-Smog-70B",
		"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 "Yobenboben/L3.3-Smog-70B" \
        --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": "Yobenboben/L3.3-Smog-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yobenboben/L3.3-Smog-70B with Docker Model Runner:
```
docker model run hf.co/Yobenboben/L3.3-Smog-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Smog

Tried out some obscure merge method. Turned out decent enough. The result is something averaged from three selected models, without any of them being too prevalent.

Distinct prose and (imo) best ERP out of the L3.3 models.

Settings:

Temp 1.05, minP 0.01

Quants:

https://huggingface.co/mradermacher/L3.3-Smog-70B-GGUF

https://huggingface.co/mradermacher/L3.3-Smog-70B-i1-GGUF

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: zerofata/L3.3-GeneticLemonade-Unleashed-v2.1-70B
  - model: allura-org/Bigger-Body-70b
  - model: Nohobby/L3.3-Prikol-70B-v0.5
merge_method: karcher
parameters:
  max_iter: 18
  tol: 1e-8
normalize: true
int8_mask: true
dtype: bfloat16

Downloads last month: 1

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for Yobenboben/L3.3-Smog-70B

Nohobby/L3.3-Prikol-70B-v0.5

allura-org/Bigger-Body-70b

zerofata/L3.3-GeneticLemonade-Unleashed-v2.1-70B

Merge model

this model

Quantizations

2 models