Instructions to use saishf/Llama4Some-SOVL-4x8B-L3-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saishf/Llama4Some-SOVL-4x8B-L3-V1 with Transformers:

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

pipe = pipeline("text-generation", model="saishf/Llama4Some-SOVL-4x8B-L3-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saishf/Llama4Some-SOVL-4x8B-L3-V1")
model = AutoModelForCausalLM.from_pretrained("saishf/Llama4Some-SOVL-4x8B-L3-V1")
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

vLLM

How to use saishf/Llama4Some-SOVL-4x8B-L3-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saishf/Llama4Some-SOVL-4x8B-L3-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": "saishf/Llama4Some-SOVL-4x8B-L3-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saishf/Llama4Some-SOVL-4x8B-L3-V1

SGLang

How to use saishf/Llama4Some-SOVL-4x8B-L3-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 "saishf/Llama4Some-SOVL-4x8B-L3-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": "saishf/Llama4Some-SOVL-4x8B-L3-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 "saishf/Llama4Some-SOVL-4x8B-L3-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": "saishf/Llama4Some-SOVL-4x8B-L3-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use saishf/Llama4Some-SOVL-4x8B-L3-V1 with Docker Model Runner:
```
docker model run hf.co/saishf/Llama4Some-SOVL-4x8B-L3-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

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

Merge Details

This model is a merge of all of my SOVL models, in the hopes to create the most unhinged and wild model possible. But in Mixtral fashion!

It may be insane, it may be incoherent. I can't load it :3

Merge Method

This model was merged using the Mixture Of Experts method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: saishf/Ortho-SOVL-8B-L3
gate_mode: random
dtype: bfloat16
experts:
  - source_model: saishf/Ortho-SOVL-8B-L3
  - source_model: saishf/SOVLish-Maid-L3-8B
  - source_model: saishf/Merge-Mayhem-L3-V2.1
  - source_model: saishf/Merge-Mayhem-L3-V2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	66.76
AI2 Reasoning Challenge (25-Shot)	61.95
HellaSwag (10-Shot)	79.38
MMLU (5-Shot)	65.49
TruthfulQA (0-shot)	51.48
Winogrande (5-shot)	75.69
GSM8k (5-shot)	66.57