Instructions to use recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp with Transformers:

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

pipe = pipeline("text-generation", model="recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp")
model = AutoModelForCausalLM.from_pretrained("recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp")
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 recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp

SGLang

How to use recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp 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 "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp" \
    --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": "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp",
		"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 "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp" \
        --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": "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp with Docker Model Runner:
```
docker model run hf.co/recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma-2-Ataraxy-Gemmasutra-9B-slerp

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.87
IFEval (0-Shot)	76.49
BBH (3-Shot)	42.25
MATH Lvl 5 (4-Shot)	1.74
GPQA (0-shot)	10.74
MuSR (0-shot)	12.39
MMLU-PRO (5-shot)	35.63

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric	Value
Average	73.97
ENEM Challenge (No Images)	75.65
BLUEX (No Images)	64.26
OAB Exams	53.76
Assin2 RTE	93.21
Assin2 STS	80.91
FaQuAD NLI	77.39
HateBR Binary	87.61
PT Hate Speech Binary	66.84
tweetSentBR	66.14

Downloads last month: 11

Model tree for recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp

Merges

2 models

Quantizations

6 models

Space using recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerp 1

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

76.490
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

42.250
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

1.740
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

10.740
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

12.390
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

35.630
accuracy on ENEM Challenge (No Images)
Open Portuguese LLM Leaderboard

75.650
accuracy on BLUEX (No Images)
Open Portuguese LLM Leaderboard

64.260