Instructions to use lemon07r/Gemma-2-Ataraxy-v4b-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lemon07r/Gemma-2-Ataraxy-v4b-9B with Transformers:

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

pipe = pipeline("text-generation", model="lemon07r/Gemma-2-Ataraxy-v4b-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lemon07r/Gemma-2-Ataraxy-v4b-9B")
model = AutoModelForCausalLM.from_pretrained("lemon07r/Gemma-2-Ataraxy-v4b-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 lemon07r/Gemma-2-Ataraxy-v4b-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lemon07r/Gemma-2-Ataraxy-v4b-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": "lemon07r/Gemma-2-Ataraxy-v4b-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lemon07r/Gemma-2-Ataraxy-v4b-9B

SGLang

How to use lemon07r/Gemma-2-Ataraxy-v4b-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 "lemon07r/Gemma-2-Ataraxy-v4b-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": "lemon07r/Gemma-2-Ataraxy-v4b-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 "lemon07r/Gemma-2-Ataraxy-v4b-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": "lemon07r/Gemma-2-Ataraxy-v4b-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lemon07r/Gemma-2-Ataraxy-v4b-9B with Docker Model Runner:
```
docker model run hf.co/lemon07r/Gemma-2-Ataraxy-v4b-9B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma-2-Ataraxy-v4b-9B

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

Leaderboard Results

Bugged?

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:

base_model: lemon07r/Gemma-2-Ataraxy-v3b-9B
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 42]
    model: zelk12/recoilme-gemma-2-Ataraxy-9B-v0.1-t0.25
  - layer_range: [0, 42]
    model: lemon07r/Gemma-2-Ataraxy-v3b-9B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	31.05
IFEval (0-Shot)	68.78
BBH (3-Shot)	43.44
MATH Lvl 5 (4-Shot)	8.84
GPQA (0-shot)	12.08
MuSR (0-shot)	15.87
MMLU-PRO (5-shot)	37.30

Downloads last month: 2

Safetensors

Model size

10B params

Tensor type

BF16

Model tree for lemon07r/Gemma-2-Ataraxy-v4b-9B

lemon07r/Gemma-2-Ataraxy-v3b-9B

zelk12/recoilme-gemma-2-Ataraxy-9B-v0.1-t0.25

Merge model

this model

Quantizations

2 models

Evaluation results

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

68.780
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

43.440
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

8.840
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

12.080
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

15.870
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

37.300