Mistrall Small 3.1 released
PSA: c4ai-command-a-03-2025 seems to be trained for reasoning / "thinking"
I hope uncensored gemma3b come soon enough... the model is unbearable boring as it is know.
KoboldCPP 1.86 just dropped with support of Gemma-3
Gemma 3 Fine-tuning now in Unsloth - 1.6x faster with 60% less VRAM
Gemma 3 27B
Drummer's Gemmasutra Small 4B v1 - The best portable RP model is back with a heftier punch!
[Megathread] - Best Models/API discussion - Week of: March 10, 2025
Which major open source model will be next? Llama, Mistral, Hermes, Nemotron, Qwen or Grok2?
Better than Deepseek, New QwQ-32B, Thanx Qwen,
Sharing my richest post-apocalyptic AI world so far (text-based rimworld?)
Cydonia 24B v2.1 - Bolder, better, brighter
[Megathread] - Best Models/API discussion - Week of: March 03, 2025
Reasoning Models - Helpful or Detrimental for Creative Writing?
Drummer's Fallen Llama 3.3 R1 70B v1 - Experience a totally unhinged R1 at home!
[Megathread] - Best Models/API discussion - Week of: February 24, 2025
Drummer's Cydonia 24B v2 - An RP finetune of Mistral Small 2501!
PerplexityAI releases R1-1776, a DeepSeek-R1 finetune that removes Chinese censorship while maintaining reasoning capabilities
Drummer's Skyfall 36B v2 - An upscale of Mistral's 24B 2501 with continued training; resulting in a stronger, 70B-like model!