Instructions to use Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp with Transformers:

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

pipe = pipeline("text-generation", model="Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp")
model = AutoModelForCausalLM.from_pretrained("Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

SGLang

How to use Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp 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 "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp with Docker Model Runner:
```
docker model run hf.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenHermes-2.5-neural-chat-v3-3-Slerp

This is the model for OpenHermes-2.5-neural-chat-v3-3-Slerp. I used mergekit to merge models.

Prompt Templates

You can use these prompt templates, but I recommend using ChatML.

ChatML (OpenHermes-2.5-Mistral-7B):

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

neural-chat-7b-v3-3

### System:
{system}
### User:
{user}
### Assistant:

Yaml Config to reproduce

slices:
  - sources:
      - model: teknium/OpenHermes-2.5-Mistral-7B
        layer_range: [0, 32]
      - model: Intel/neural-chat-7b-v3-3
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

Quantizationed versions

Quantizationed versions of this model is available thanks to TheBloke.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.38
ARC (25-shot)	68.09
HellaSwag (10-shot)	86.2
MMLU (5-shot)	64.26
TruthfulQA (0-shot)	62.78
Winogrande (5-shot)	79.16
GSM8K (5-shot)	67.78

If you would like to support me:

☕ Buy Me a Coffee

Downloads last month: 66

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

Intel/neural-chat-7b-v3-3

teknium/OpenHermes-2.5-Mistral-7B

Merge model

this model

Adapters

2 models

Merges

7 models

Quantizations

6 models

Space using Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp 1

Collection including Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

Merge models

Collection

Merge models created with mergekit • 19 items • Updated Dec 3, 2025 • 3

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set self-reported

68.090
normalized accuracy on HellaSwag (10-Shot)
validation set self-reported

86.200
accuracy on MMLU (5-Shot)
test set self-reported

64.260
mc2 on TruthfulQA (0-shot)
validation set self-reported

62.780
accuracy on Winogrande (5-shot)
validation set self-reported

79.160
accuracy on GSM8k (5-shot)
test set self-reported

67.780