Instructions to use grimjim/Gemma2-Nephilim-v3-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Gemma2-Nephilim-v3-9B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Gemma2-Nephilim-v3-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Gemma2-Nephilim-v3-9B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Gemma2-Nephilim-v3-9B")
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 grimjim/Gemma2-Nephilim-v3-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Gemma2-Nephilim-v3-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/Gemma2-Nephilim-v3-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Gemma2-Nephilim-v3-9B

SGLang

How to use grimjim/Gemma2-Nephilim-v3-9B 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 "grimjim/Gemma2-Nephilim-v3-9B" \
    --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": "grimjim/Gemma2-Nephilim-v3-9B",
		"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 "grimjim/Gemma2-Nephilim-v3-9B" \
        --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": "grimjim/Gemma2-Nephilim-v3-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Gemma2-Nephilim-v3-9B with Docker Model Runner:
```
docker model run hf.co/grimjim/Gemma2-Nephilim-v3-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma2-Nephilim-v3-9B

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

Though none of the components of this merge were trained for roleplay nor intended for it, the model can be used effectively in that role.

Tested with temperature 1 and minP 0.01. This model leans toward being creative, so adjust temperature upward or downward as desired. The Instruct template used during testing can be found below:

Afterword: In subsequent testing, I encountered an occasional lapse in tracking context for complex scenarios, which seems to originate in the SPPO model. This lapse is not present in grimjim/Kitsunebi-v1-Gemma2-8k-9B.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: princeton-nlp/gemma-2-9b-it-SimPO
    layer_range:
    - 0
    - 42
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    layer_range:
    - 0
    - 42
merge_method: slerp
base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
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
dtype: bfloat16

Downloads last month: 9

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for grimjim/Gemma2-Nephilim-v3-9B

UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3

princeton-nlp/gemma-2-9b-it-SimPO

Merge model

this model

Merges

2 models

Quantizations

4 models