Instructions to use allura-org/G2-9B-Aletheia-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-org/G2-9B-Aletheia-v1 with Transformers:

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

pipe = pipeline("text-generation", model="allura-org/G2-9B-Aletheia-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allura-org/G2-9B-Aletheia-v1")
model = AutoModelForCausalLM.from_pretrained("allura-org/G2-9B-Aletheia-v1", 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 allura-org/G2-9B-Aletheia-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-org/G2-9B-Aletheia-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/G2-9B-Aletheia-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allura-org/G2-9B-Aletheia-v1

SGLang

How to use allura-org/G2-9B-Aletheia-v1 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 "allura-org/G2-9B-Aletheia-v1" \
    --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": "allura-org/G2-9B-Aletheia-v1",
		"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 "allura-org/G2-9B-Aletheia-v1" \
        --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": "allura-org/G2-9B-Aletheia-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allura-org/G2-9B-Aletheia-v1 with Docker Model Runner:
```
docker model run hf.co/allura-org/G2-9B-Aletheia-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

_{Image by CalamitousFelicitousness}

Gemma-2-9B Aletheia v1

A merge of Sugarquill and Sunfall. I wanted to combine Sugarquill's more novel-like writing style with something that would improve it's RP perfomance and make it more steerable, w/o adding superfluous synthetic writing patterns.

I quite like Crestfall's Sunfall models and I felt like Gemma version of Sunfall will steer the model in this direction when merged in. To keep more of Gemma-2-9B-it-SPPO-iter3's smarts, I've decided to apply Sunfall LoRA on top of it, instead of using the published Sunfall model.

I'm generally pleased with the result, this model has nice, fresh writing style, good charcard adherence and good system prompt following. It still should work well for raw completion storywriting, as it's a trained feature in both merged models.

Made by Auri.

Thanks to Prodeus, Inflatebot and ShotMisser for testing and giving feedback.

Format

Model responds to Gemma instruct formatting, exactly like it's base model.

<bos><start_of_turn>user
{user message}<end_of_turn>
<start_of_turn>model
{response}<end_of_turn><eos>

Mergekit config

The following YAML configuration was used to produce this model:

models:
  - model: allura-org/G2-9B-Sugarquill-v0
    parameters:
      weight: 0.55
      density: 0.4
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3+AuriAetherwiing/sunfall-g2-lora
    parameters:
      weight: 0.45
      density: 0.3
merge_method: ties
base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
parameters:
  normalize: true
dtype: bfloat16

Downloads last month: 20

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for allura-org/G2-9B-Aletheia-v1

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

allura-org/G2-9B-Sugarquill-v0

crestf411/gemma2-9B-sunfall-v0.5.2

Merge model

this model

Merges

5 models

Quantizations

4 models