Downloads · 30 days
0
chakibmed/whispbook-qwen3-4b-speaker-lora-speaker_lora_v1_easy_evidence_only_cleaned
whispbook-qwen3-4b-speaker-lora-speaker_lora_v1_easy_evidence_only_cleaned is a machine learning model from chakibmed. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
LoRA adapter for speaker attribution on top of Qwen/Qwen3-4B-Instruct-2507.
Downloads · 30 days
0
Access
Public
Updated May 16, 2026
Repo size
126 MB
Likes
0
Public
Click a slice to open those files.
.safetensors136 MB · 100%
From the Hugging Face model README
LoRA adapter for speaker attribution on top of Qwen/Qwen3-4B-Instruct-2507.
Training base: mlx-community/Qwen3-4B-Instruct-2507-4bit.
import mlx_lm
model, tokenizer = mlx_lm.load("mlx-community/Qwen3-4B-Instruct-2507-4bit", adapter_path="path/to/adapter")
speaker_lora_v1_easy_evidence_only_cleanedspeaker_lora_v1_easy_evidence_onlyoutputs/qwen_json_v1_easy/test.jsonldialogue_accuracy: passparse_rate: passtop_prediction_rate: failvalid_candidate_id_rate: passadapter/: MLX LoRA adapter files and checkpoint snapshots.configs/: MLX training config used for this run.reports/: held-out predictions and summary metrics.journals/: local training/evaluation journals.