Fmuaddib/YiSM-34B-0rn-mlx-8Bit
The Model Fmuaddib/YiSM-34B-0rn-mlx-8Bit was converted to MLX format from altomek/YiSM-34B-0rn using mlx-lm version 0.22.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Fmuaddib/YiSM-34B-0rn-mlx-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
- 18
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Fmuaddib/YiSM-34B-0rn-mlx-8Bit
Base model
altomek/YiSM-34B-0rnEvaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard69.540
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.670
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard78.510
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard59.680
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard83.660
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard75.820
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard42.840
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard45.380
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard20.620
- acc_norm on GPQA (0-shot)Open LLM Leaderboard16.220