Instructions to use anjohn0077/NEXS-llama-3.1-8b-multislerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anjohn0077/NEXS-llama-3.1-8b-multislerp with Transformers:

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

pipe = pipeline("text-generation", model="anjohn0077/NEXS-llama-3.1-8b-multislerp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anjohn0077/NEXS-llama-3.1-8b-multislerp")
model = AutoModelForCausalLM.from_pretrained("anjohn0077/NEXS-llama-3.1-8b-multislerp")
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 anjohn0077/NEXS-llama-3.1-8b-multislerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anjohn0077/NEXS-llama-3.1-8b-multislerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anjohn0077/NEXS-llama-3.1-8b-multislerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anjohn0077/NEXS-llama-3.1-8b-multislerp

SGLang

How to use anjohn0077/NEXS-llama-3.1-8b-multislerp 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 "anjohn0077/NEXS-llama-3.1-8b-multislerp" \
    --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": "anjohn0077/NEXS-llama-3.1-8b-multislerp",
		"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 "anjohn0077/NEXS-llama-3.1-8b-multislerp" \
        --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": "anjohn0077/NEXS-llama-3.1-8b-multislerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anjohn0077/NEXS-llama-3.1-8b-multislerp with Docker Model Runner:
```
docker model run hf.co/anjohn0077/NEXS-llama-3.1-8b-multislerp
```

NEXS Llama-3.1-8B Multi-SLERP Merge

A multi-SLERP merge of LlamaForCausalLM domain experts covering finance, medical, legal, safety/toxicity, and truthfulness, produced with mergekit. Part of the NEXS multi-SLERP merge collection.

Method

Multi-SLERP (multislerp) performs barycentric spherical interpolation on a hypersphere for more than two models: it projects the models into the tangent space at their weighted Euclidean mean, interpolates, and projects back. Here it is run in task-vector space — each source's delta from the shared base model is computed, the deltas are spherically averaged with equal weight (normalize_weights: true, eps: 1e-8), and the result is added back to the base. Merging was done with mergekit.

Variants had minor vocab differences (128256/128257/128258); tokenizer_source: base reconciled all embeddings to the base tokenizer.

Sources

Base model (task-vector reference): meta-llama/Llama-3.1-8B-Instruct

Merged variants (equal weight 1.0 each):

mergekit config

merge_method: multislerp
base_model: meta-llama/Llama-3.1-8B-Instruct
tokenizer_source: base
dtype: float32
out_dtype: bfloat16
parameters:
  normalize_weights: true
  eps: 1.0e-8
models:
  - model: mukaj/Llama-3.1-Hawkish-8B
    parameters: {weight: 1.0}
  - model: TsinghuaC3I/Llama-3.1-8B-UltraMedical
    parameters: {weight: 1.0}
  - model: MaziyarPanahi/calme-2.3-legalkit-8b
    parameters: {weight: 1.0}
  - model: K-intelligence/Llama-SafetyGuard-Content-Binary
    parameters: {weight: 1.0}
  - model: HiTZ/Llama-3.1-8B-Instruct-multi-truth-judge
    parameters: {weight: 1.0}

Downloads last month: 225

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for anjohn0077/NEXS-llama-3.1-8b-multislerp

HiTZ/Llama-3.1-8B-Instruct-multi-truth-judge

K-intelligence/Llama-SafetyGuard-Content-Binary

MaziyarPanahi/calme-2.3-legalkit-8b

TsinghuaC3I/Llama-3.1-8B-UltraMedical

meta-llama/Llama-3.1-8B-Instruct

mukaj/Llama-3.1-Hawkish-8B

Merge model

this model