A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
154.9K Pulls 35 Tags Updated 1 year ago
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
133.4K Pulls 17 Tags Updated 1 year ago
This project fine-tunes the Qwen2-1.5B model for Arabic language tasks using Quantized LoRA (QLoRA).
897 Pulls 1 Tag Updated 1 year ago
LoRA-merged abliterated L3.1-8B GGUF from https://huggingface.co/grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF/tree/main
838 Pulls 1 Tag Updated 1 year ago
Modelo de lenguaje en español para generar artículos detallados optimizado con LoRA y cuantización de 4 bits.
450 Pulls 1 Tag Updated 1 year ago
LoRA-адаптер для модели YandexGPT-5-Lite-8B-pretrain обученный на миксе из датасетов реализующих r1 (ризонинг) подход.
345 Pulls 7 Tags Updated 9 months ago
Model finetuned starting with llama 3.1 8b using a full precision LoRA he20, rank 64, alpha 16
273 Pulls 1 Tag Updated 1 year ago
235 Pulls 1 Tag Updated 1 year ago
QWen2-based command-line assistant model fine-tuned using LoRA and 4-bit quantization, optimized for generating Unix/Linux commands with a simple prompt format and explicit stop sequences.
203 Pulls 1 Tag Updated 1 year ago
unc-QLoRA
130 Pulls 1 Tag Updated 9 months ago
quantization of seedboxai/KafkaLM-7B-DARE_TIES-LaserRMT-QLoRA-DPO-v0.5 - trained on 8k of seedboxai/multitask_german_examples_32k
103 Pulls 1 Tag Updated 1 year ago
Build Ollama For Reranker_v2 (LoRA BERT）
102 Pulls 2 Tags Updated 4 months ago
AI4Bharat/BPCC( SFT,LoRA/PeFT) on gemma3
102 Pulls 3 Tags Updated 6 months ago
A Mistral Nemo model finetuned using 8bit QLoRA using a medical questions database
67 Pulls 1 Tag Updated 1 year ago
LoRA-finetuned Qwen3 8B for Czech Home Assistant. HomeQwen3
58 Pulls 1 Tag Updated 2 months ago
Llama 3.2 with nvidia/HelpSteer2 LoRA this thing is one smart llama
46 Pulls 1 Tag Updated 1 year ago
Suntray-Qwen3 is fine-tuned from Qwen-3 using LoRA, making it the first hybrid reasoning model that integrates fast thinking (System 1) and slow thinking (System 2). Its performance surpasses leading open-source models.
41 Pulls 1 Tag Updated 5 months ago
fgptech_2.5-1.5b-code-review Modèle dérivé de Qwen/Qwen2.5-1.5B-Instruct, fine-tuné (SFT + LoRA → fusionné) pour la revue de code (FR) au format strict Markdown.
13 Pulls 1 Tag Updated 3 months ago
LoRA-finetuned Qwen3 8B model for Czech language.
12 Pulls 1 Tag Updated 2 weeks ago
8 Pulls 1 Tag Updated 10 months ago