Asclepio-8B
Asclepio-8B is a fine-tuned version of huihui-ai/DeepSeek-R1-0528-Qwen3-8B-abliterated specialized in medical reasoning and clinical decision-making. Trained with high-quality data...
Метка: deepseek-r1
deepseek-r1
— no more error loading message: «unknown pre-tokenizer type: deepseek-r1-qwen» — works fine for llama architecture use any...
DeepSeek-R1-Distill-Qwen-32B-Q5_K_M-GGUF
Repo: roleplaiapp/DeepSeek-R1-Distill-Qwen-32B-Q5KM-GGUF Original Model: DeepSeek-R1-Distill-Qwen-32B Organization: deepseek-ai Quantized File: deepseek-r1-distill-qwen-32b-q5km.gguf Quantization: GGUF Quantization Method: Q5KM Use Imatrix: False...
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M-GGUF
Repo: roleplaiapp/DeepSeek-R1-Distill-Qwen-7B-Q4KM-GGUF Original Model: DeepSeek-R1-Distill-Qwen-7B Organization: deepseek-ai Quantized File: deepseek-r1-distill-qwen-7b-q4km.gguf Quantization: GGUF Quantization Method: Q4KM Use Imatrix: False...
DeepSeek-R1-Distill-Qwen-7B
LiteRT is Google’s on-device runtime, the new name for TensorFlow Lite (Android: com.google.ai.edge.litert:litert), and litert-torch, the renamed ai-edge-torch,...
DeepSeek-R1-0528-Qwen3-8B-Medical-Reasoning
This project fine-tunes the deepseek-ai/DeepSeek-R1-0528-Qwen3-8B model using a medical reasoning dataset (mamachang/medical-reasoning) with 4-bit quantization for memory-efficient training....
Arabic-DeepSeek-R1-Distill-8B
DeepSeek-R1-Distill-Llama-8B (Arabic Reasoning Edition) is a fine-tuned version of the base model unsloth/DeepSeek-R1-Distill-Llama-8B that has been further optimized...
deepSQL-R1-distill-8B
State-of-the-art advances in LLMs have pushed NLP to its limits, where even complex tasks, such as code generation,...
RAI-3.0-R1-VECTOR
— Может наследовать предвзятости от любой исходной модели. — Исполнение на неяпонском/английском языках может отличаться. — Всегда проверяйте...
RareSeek-R1
🧬 RareSeek-R1 Специализированная языковая модель для диагностики редких заболеваний и клинического рассуждения RareSeek-R1 — это специализированная модель большого...