Instructions to use jsfs11/WestOrcaNeural-V2-DARETIES-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsfs11/WestOrcaNeural-V2-DARETIES-7B with Transformers:

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

pipe = pipeline("text-generation", model="jsfs11/WestOrcaNeural-V2-DARETIES-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("jsfs11/WestOrcaNeural-V2-DARETIES-7B")
model = AutoModelForMultimodalLM.from_pretrained("jsfs11/WestOrcaNeural-V2-DARETIES-7B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jsfs11/WestOrcaNeural-V2-DARETIES-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsfs11/WestOrcaNeural-V2-DARETIES-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsfs11/WestOrcaNeural-V2-DARETIES-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jsfs11/WestOrcaNeural-V2-DARETIES-7B

SGLang

How to use jsfs11/WestOrcaNeural-V2-DARETIES-7B 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 "jsfs11/WestOrcaNeural-V2-DARETIES-7B" \
    --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": "jsfs11/WestOrcaNeural-V2-DARETIES-7B",
		"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 "jsfs11/WestOrcaNeural-V2-DARETIES-7B" \
        --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": "jsfs11/WestOrcaNeural-V2-DARETIES-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jsfs11/WestOrcaNeural-V2-DARETIES-7B with Docker Model Runner:
```
docker model run hf.co/jsfs11/WestOrcaNeural-V2-DARETIES-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WestOrcaNeural-V2-DARETIES-7B

WestOrcaNeural-V2-DARETIES-7B is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
    parameters:
      density: 0.6
      weight: 0.35
  - model: senseable/WestLake-7B-v2
    parameters:
      density: 0.65
      weight: 0.4
  - model: mlabonne/NeuralBeagle14-7B
    parameters:
      density: 0.55
      weight: 0.25
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.53
AI2 Reasoning Challenge (25-Shot)	72.10
HellaSwag (10-Shot)	88.21
MMLU (5-Shot)	64.64
TruthfulQA (0-shot)	67.81
Winogrande (5-shot)	83.74
GSM8k (5-shot)	70.66

Downloads last month: 56

Safetensors

Model size

7B params

Tensor type

F16

Model tree for jsfs11/WestOrcaNeural-V2-DARETIES-7B

Quantizations

2 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

72.100
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.210
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.640
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

67.810
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.740
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

70.660