ModelPublicadoExterno

Exegen Qwen14b v2 LoRA

QLoRA adapter for exegetical generation (terse Sanskrit → expansive English commentary), fine-tuned on the expanded ExeGen train set.

Fuentehuggingface.co/Anamavajra-Labs/exegen-qwen14b-v2-lora/tree/68fcc0f9ad5c688cae0828bed345c19f87761383

TipoLoRAModelo baseQwen/Qwen2.5-14B-InstructVersiónadapter_modelBcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 131 MB
Modelo base: Qwen/Qwen2.5-14B-Instruct
Versión: vadapter_model
Actualizado: 5 oct 2026
Descargas: 6
Fuente: Hugging Face

Descripción de la fuente

ExeGen Qwen2.5-14B v2 — QLoRA (2021-expanded)

QLoRA adapter for exegetical generation (terse Sanskrit → expansive English commentary), fine-tuned on the expanded ExeGen train set.

Base: Qwen/Qwen2.5-14B-Instruct (4-bit nf4, QLoRA r=16, α=32, 3 epochs)
Train: 1,594 pairs (704 original + 890 new verse→oral-commentary pairs from Mark Dyczkowski's 2021 Tantrāloka ch5/7/8/9/10 lectures), vs the v1 adapter's 704.
Trained on Brev (7×H100 DDP, ~9 min) — successor to exegen-qwen14b-lora.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct", device_map="auto")
model = PeftModel.from_pretrained(base, "Anamavajra-Labs/exegen-qwen14b-v2-lora")

Related: 📄 paper · 🗂️ corpus

Fuentes

1 fuente

Hugging FacePrincipalVersión 68fcc0f9ad5c688cae0828bed345c19f87761383

huggingface.co/Anamavajra-Labs/exegen-qwen14b-v2-lora/tree/68fcc0f9ad5c688cae0828bed345c19f87761383

Verificado 23 ago

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 131 MB · SHA-256 25167fc9e3b9…711d · Hugging Face

Download file

Extractos de fuentes

2 extractos

Readme23 agohuggingface.co/Anamavajra-Labs/exegen-qwen14b-v2-lora

--- license: apache-2.0 base_model: Qwen/Qwen2.5-14B-Instruct library_name: peft language: [sa, en] tags: [sanskrit, exegetical-generation, kashmir-shaivism, tantraloka, kubjika, lora, qlora, nlp, indology] datasets: [Anamavajra-Labs/tantraloka-dyczkowski-raw] --- # ExeGen Qwen2.5-14B v2 — QLoRA (2021-expanded) QLoRA adapter for **exegetical generation** (terse Sanskrit → expansive English commentary), fine-tuned on the **expanded** ExeGen train set. - **Base:** Qwen/Qwen2.5-14B-Instruct (4-bit nf4, QLoRA r=16, α=32, 3 epochs) - **Train:** 1,594 pairs (704 original + **890 new verse→oral-commentary pairs** from Mark Dyczkowski's 2021 Tantrāloka ch5/7/8/9/10 lectures), vs the v1 adapter's 704. - **Trained on Brev** (7×H100 DDP, ~9 min) — successor to [`exegen-qwen14b-lora`](https://huggingface.co/Anamavajra-Labs/exegen-qwen14b-lora). ## Usage ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct", device_map="auto") model = PeftModel.from_pretrained(base, "Anamavajra-Labs/exegen-qwen14b-v2-lora") ``` Related: 📄 [paper](https://huggingface.co/Anamavajra-Labs/exegetical-generation-paper) · 🗂️ [corpus](https://huggingface.co/datasets/Anamavajra-Labs/tantraloka-dyczkowski-raw)

Note23 agohuggingface.co/Anamavajra-Labs/exegen-qwen14b-v2-lora

Source context: 6 downloads · 0 likes · Library peft · Repo Anamavajra-Labs/exegen-qwen14b-v2-lora