recoilme-gemma-2-9B-v0.2
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "recoilme/recoilme-gemma-2-9B-v0.2"
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. | 30.05 |
| IFEval (0-Shot) | 75.92 |
| BBH (3-Shot) | 43.03 |
| MATH Lvl 5 (4-Shot) | 5.29 |
| GPQA (0-shot) | 10.51 |
| MuSR (0-shot) | 10.40 |
| MMLU-PRO (5-shot) | 35.15 |
- Downloads last month
- 3,764
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for recoilme/recoilme-gemma-2-9B-v0.2
Space using recoilme/recoilme-gemma-2-9B-v0.2 1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard75.920
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard43.030
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.290
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.510
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.400
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard35.150