Instructions to use grimjim/Magot-v1-Gemma2-8k-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Magot-v1-Gemma2-8k-9B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Magot-v1-Gemma2-8k-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Magot-v1-Gemma2-8k-9B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Magot-v1-Gemma2-8k-9B", device_map="auto")
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/Magot-v1-Gemma2-8k-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Magot-v1-Gemma2-8k-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/Magot-v1-Gemma2-8k-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Magot-v1-Gemma2-8k-9B

SGLang

How to use grimjim/Magot-v1-Gemma2-8k-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/Magot-v1-Gemma2-8k-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/Magot-v1-Gemma2-8k-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/Magot-v1-Gemma2-8k-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/Magot-v1-Gemma2-8k-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Magot-v1-Gemma2-8k-9B with Docker Model Runner:
```
docker model run hf.co/grimjim/Magot-v1-Gemma2-8k-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Magot-v1-Gemma2-8k-9B

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

This model is an experiment in using merger as a method of making an Instruct-heavy model less constrained in its text generation.

Tested at temp=1, minP=0.01. Coherence is high, though not perfect. The low weight (0.2) infusion of the Magnum model provided needed variety to text generation. This model is being released because it is "good enough" and interesting. Inherent model safety is still strong due to Instruct base, but narratives are less bounded by positivity.

When used, metadata link backs to this model are appreciated. The motivation is curiosity regarding what people do with this.

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: grimjim/Kitsunebi-v1-Gemma2-8k-9B
    layer_range: [0, 42]
  - model: anthracite-org/magnum-v3-9b-customgemma2
    layer_range: [0, 42]
merge_method: slerp
base_model: grimjim/Kitsunebi-v1-Gemma2-8k-9B
parameters:
  t:
   - value: 0.2
dtype: bfloat16