mlx-community/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
The Model mlx-community/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 was converted to MLX format from Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 using mlx-lm version 0.18.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2")
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
- 15
Inference API (serverless) does not yet support mlx models for this pipeline type.
Model tree for mlx-community/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Base model
Qwen/Qwen2.5-7BEvaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard78.410
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard33.290
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.490
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.960
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard34.760