kaptaan45/QaptaanLM-0.75B-Instruct

Text Generation • 0.8B • Updated about 1 hour ago • 489

Note Supervised Fine-Tuned (SFT) Master Model (752M params)

kaptaan45/QaptaanLM-0.75B

Text Generation • 0.8B • Updated about 1 hour ago • 501

Note Continued Pre-Trained (CPT) Base Foundation Model (752M params)

kaptaan45/QaptaanLM-0.75B-Instruct-GGUF

Text Generation • 0.8B • Updated about 1 hour ago • 56

Note All GGUF quantizations for llama.cpp & Ollama (SFT)

kaptaan45/QaptaanLM-0.75B-GGUF

Text Generation • 0.8B • Updated about 1 hour ago • 35

Note All GGUF quantizations for llama.cpp & Ollama (Base)

kaptaan45/QaptaanLM-0.75B-Instruct-BnB

Text Generation • Updated about 1 hour ago

Note Unified 4-Bit NF4 & 8-Bit Int8 BitsAndBytes suite (SFT)

kaptaan45/QaptaanLM-0.75B-BnB

Text Generation • Updated about 1 hour ago

Note Unified 4-Bit NF4 & 8-Bit Int8 BitsAndBytes suite (Base)

kaptaan45/QaptaanLM-0.75B-Instruct-ONNX

Text Generation • Updated about 1 hour ago

Note ONNX & WebGPU client-side / in-browser export (SFT)

kaptaan45/QaptaanLM-0.75B-ONNX

Text Generation • Updated about 1 hour ago

Note ONNX & WebGPU client-side / in-browser export (Base)

Note 1 Billion Token CPT Programming & Technical Dataset

Note Multi-turn Instruction Tuning Dataset