TheBlueObserver/Falcon3-10B-Instruct-MLX
The Model TheBlueObserver/Falcon3-10B-Instruct-MLX was converted to MLX format from tiiuae/Falcon3-10B-Instruct using mlx-lm version 0.20.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("TheBlueObserver/Falcon3-10B-Instruct-MLX")
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
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for TheBlueObserver/Falcon3-10B-Instruct-MLX
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard78.170
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard44.820
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard25.910
- acc_norm on GPQA (0-shot)Open LLM Leaderboard10.510
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.610
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard38.100