Foundation Text-Generation Models Below 360M Parameters
Collection
Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. • 101 items • Updated • 47
🔄 In a Training Loop
Charles
qikp
AI & ML interests
Training smaller models and fighting tooth and nail against underfitting.
Recent Activity
updated a dataset about 2 hours ago
qikp/wildchat-english published a dataset about 2 hours ago
qikp/wildchat-english new activity 2 days ago
trymirai/Qwen3.8-27B-S-experimental:Upstream to ggml and llama.cppOrganizations
None yet
upvoted a collection 3 months ago