Instructions to use beberik/Nyxene-v2-11B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beberik/Nyxene-v2-11B with Transformers:

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

pipe = pipeline("text-generation", model="beberik/Nyxene-v2-11B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beberik/Nyxene-v2-11B")
model = AutoModelForCausalLM.from_pretrained("beberik/Nyxene-v2-11B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use beberik/Nyxene-v2-11B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beberik/Nyxene-v2-11B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beberik/Nyxene-v2-11B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/beberik/Nyxene-v2-11B

SGLang

How to use beberik/Nyxene-v2-11B 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 "beberik/Nyxene-v2-11B" \
    --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": "beberik/Nyxene-v2-11B",
		"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 "beberik/Nyxene-v2-11B" \
        --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": "beberik/Nyxene-v2-11B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use beberik/Nyxene-v2-11B with Docker Model Runner:
```
docker model run hf.co/beberik/Nyxene-v2-11B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Description

This repo contains bf16 files of Nyxene-v2-11B. It feels like with the new models, 1% is no longer needed as in the previous version. And yes, new version. Again.

Model used

Prompt template

The best one after further testing is this one:

<|system|>
Below is an instruction that describes a task. Write a response that appropriately completes the request.
<|user|>
{prompt}
<|assistant|>

The secret sauce

loyal-piano-cybertron-11B :

slices:
  - sources:
    - model: fblgit/una-cybertron-7b-v2
      layer_range: [0, 24]
  - sources:
    - model: chargoddard/loyal-piano-m7-cdpo
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Starling-DPOHermes-11B :

slices:
  - sources:
    - model: berkeley-nest/Starling-LM-7B-alpha
      layer_range: [0, 24]
  - sources:
    - model: openaccess-ai-collective/DPOpenHermes-7B
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Nyxene-11B :

slices:
  - sources:
      - model: loyal-piano-cybertron-11B
        layer_range: [0, 48]
      - model: Starling-NeuralHermes-11B
        layer_range: [0, 48]
merge_method: slerp
base_model: loyal-piano-cybertron-11B
parameters:
  t:
    - filter: lm_head 
      value: [0.75]
    - filter: embed_tokens
      value: [0.75]
    - filter: self_attn
      value: [0.75, 0.25]
    - filter: mlp
      value:  [0.25, 0.75]
    - filter: layernorm
      value: [0.5, 0.5]
    - filter: modelnorm
      value: [0.75]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

I use mergekit for all the manipulation told here.

Thanks to the Undi95 for the original 11B mistral merge recipe.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.84
AI2 Reasoning Challenge (25-Shot)	67.41
HellaSwag (10-Shot)	84.54
MMLU (5-Shot)	65.26
TruthfulQA (0-shot)	55.62
Winogrande (5-shot)	79.56
GSM8k (5-shot)	54.66

Downloads last month: 201

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for beberik/Nyxene-v2-11B

Quantizations

6 models

Evaluation results

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

67.410
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

84.540
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

65.260
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

55.620
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

79.560
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

54.660