Instructions to use kromcomp/L3-Overv3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kromcomp/L3-Overv3-8B with Transformers:

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

pipe = pipeline("text-generation", model="kromcomp/L3-Overv3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kromcomp/L3-Overv3-8B")
model = AutoModelForCausalLM.from_pretrained("kromcomp/L3-Overv3-8B")
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 kromcomp/L3-Overv3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kromcomp/L3-Overv3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kromcomp/L3-Overv3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kromcomp/L3-Overv3-8B

SGLang

How to use kromcomp/L3-Overv3-8B 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 "kromcomp/L3-Overv3-8B" \
    --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": "kromcomp/L3-Overv3-8B",
		"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 "kromcomp/L3-Overv3-8B" \
        --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": "kromcomp/L3-Overv3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kromcomp/L3-Overv3-8B with Docker Model Runner:
```
docker model run hf.co/kromcomp/L3-Overv3-8B
```

over

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

Merge Details

Merge Method

This model was merged using the SCE merge method using failspy/Llama-3-8B-Instruct-MopeyMule + PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: failspy/Llama-3-8B-Instruct-MopeyMule+PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA
chat_template: llama3
dtype: float32
merge_method: sce
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: Cas-Archive/L3-Penumbral-Mind-RP-8B
      - layer_range: [0, 32]
        model: ChaoticNeutrals/T-900-8B
      - layer_range: [0, 32]
        model: failspy/Llama-3-8B-Instruct-MopeyMule+PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA
parameters:
  select_topk: 0.25
tokenizer:
  pad_to_multiple_of: 32