Natural language → MongoDB aggregation pipelines, offline: fine-tuned Qwen3.5 GGUFs. CLI: 0.8B on CPU, 4B/9B on GPU (Vulkan); 2B for llama-server.
Manuel Garcia Sanz
manuelgscom
AI & ML interests
None yet
Recent Activity
upvoted a collection 1 day ago
FactuSight upvoted a collection 1 day ago
askmdb upvoted a collection 1 day ago
daleOrganizations
None yet
Natural language → MongoDB aggregation pipelines, offline: fine-tuned Qwen3.5 GGUFs. CLI: 0.8B on CPU, 4B/9B on GPU (Vulkan); 2B for llama-server.
Offline invoice and receipt data extraction with fine-tuned Qwen3.5 vision models (GGUF, llama.cpp). Spanish invoices, JSON output.
Offline natural language → bash for Linux: fine-tuned Qwen3.5, 0.8B on CPU and 2B/4B/9B on GPU (Vulkan), for llama.cpp.