mlx-community/SuperNova-Medius-8bit
The Model mlx-community/SuperNova-Medius-8bit was converted to MLX format from arcee-ai/SuperNova-Medius using mlx-lm version 0.19.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/SuperNova-Medius-8bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for mlx-community/SuperNova-Medius-8bit
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard55.600
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.300
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard32.480
- acc_norm on GPQA (0-shot)Open LLM Leaderboard17.900
- acc_norm on MuSR (0-shot)Open LLM Leaderboard19.190
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard48.830