ModelListadosExterno

Sermon Boundary Qwen3 8b LoRA

Detects preached sermon start/end times in Episcopal/Anglican full worship service transcripts.

Fontehuggingface.co/taymoss/sermon-boundary-qwen3-8b-lora/tree/d4325a1da737fb12cd9488334ce519e0d5a80a12

TipoLoRAModelo baseQwen/Qwen3-8BVersãoadapter_modelBnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 333 MB
Modelo base: Qwen/Qwen3-8B
Versão: vadapter_model
Atualizado: 20 de out. de 2026
Downloads: 6
Fonte: Hugging Face

Descrição da fonte

Sermon Boundary Distillation (Qwen3-8B LoRA)

Detects preached sermon start/end times in Episcopal/Anglican full worship service transcripts.

Base model

Qwen/Qwen3-8B

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

base = "Qwen/Qwen3-8B"
adapter = "taymoss/sermon-boundary-qwen3-8b-lora"

tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter)

Holdout metrics (469 validation videos)

Metric	Value
parse_success_rate	n/a
detection_accuracy	n/a
mean_sermon_iou	n/a
mean_start_error_sec	n/a
mean_end_error_sec	n/a

Fontes

1 fonte

Hugging FacePrimárioVersão d4325a1da737fb12cd9488334ce519e0d5a80a12

huggingface.co/taymoss/sermon-boundary-qwen3-8b-lora/tree/d4325a1da737fb12cd9488334ce519e0d5a80a12

Verificado 20 de out.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 333 MB · SHA-256 d4875d9a3feb…8e8c · Hugging Face

Download file

Trechos de fonte

3 trechos

Readme3 de ago.huggingface.co/taymoss/sermon-boundary-qwen3-8b-lora

--- base_model: Qwen/Qwen3-8B library_name: peft tags: - lora - sermon-boundary - qwen3 - episcopal license: apache-2.0 --- # Sermon Boundary Distillation (Qwen3-8B LoRA) Detects preached sermon start/end times in Episcopal/Anglican full worship service transcripts. ## Base model `Qwen/Qwen3-8B` ## Usage ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer import torch base = "Qwen/Qwen3-8B" adapter = "taymoss/sermon-boundary-qwen3-8b-lora" tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( base, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto" ) model = PeftModel.from_pretrained(model, adapter) ``` ## Holdout metrics (469 validation videos) | Metric | Value | |--------|-------| | parse_success_rate | n/a | | detection_accuracy | n/a | | mean_sermon_iou | n/a | | mean_start_error_sec | n/a | | mean_end_error_sec | n/a |

Note20 de out.huggingface.co/taymoss/sermon-boundary-qwen3-8b-lora

Source context: 6 downloads · 1 likes · Library peft · Repo taymoss/sermon-boundary-qwen3-8b-lora

Note3 de ago.huggingface.co/taymoss/sermon-boundary-qwen3-8b-lora

Source context: 28 downloads · 0 likes · Library peft · Repo taymoss/sermon-boundary-qwen3-8b-lora