MichelRosselli

GLM-4.5-Air

GLM-4.5-Air is a hybrid reasoning model that provides two modes: a thinking mode for complex reasoning and tool use, and a non-thinking mode for immediate responses.

tools thinking

41.9K Pulls 9 Tags Updated 10 months ago

GLM-4.6

GLM-4.6 is a hybrid reasoning model that provides two modes: a thinking mode for complex reasoning and tool use, and a non-thinking mode for immediate responses.

tools thinking

5,777 Pulls 9 Tags Updated 7 months ago

apertus

Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.

tools thinking

3,570 Pulls 5 Tags Updated 1 month ago

grok-2

Grok 2, a model trained and used at xAI in 2024.

3,346 Pulls 8 Tags Updated 9 months ago

minimax-m2

1,455 Pulls 9 Tags Updated 7 months ago

apriel-1.5-15b-thinker

Apriel-1.5-15b-Thinker is a multimodal reasoning model in ServiceNow’s Apriel SLM series which achieves competitive performance against models 10 times it's size.

vision

1,132 Pulls 4 Tags Updated 9 months ago

ternary-bonsai

Ternary Bonsai: 1.58-bit Language Models at 8B, 4B, and 1.7B Scale.

tools thinking

198 Pulls 4 Tags Updated 1 month ago

GLM-4.6-REAP-218B-A32B-FP8-mixed-AutoRound

This model is a mixed gguf q2ks format of Cerebras' GLM-4.6-REAP-218B-A32B-FP8 generated using Intel's AutoRound algorithm.

tools thinking

161 Pulls 1 Tag Updated 8 months ago

GLM-4.6-REAP-268B-A32B

GLM-4.6-REAP-268B-A32B (by Cerebras), a memory-efficient compressed variant of GLM-4.6 that maintains near-identical performance while being 25% lighter.

tools thinking

133 Pulls 9 Tags Updated 7 months ago

apertus-v1.1

Apertus-v1.1 is a series of highly efficient, 0.5-4B billion parameter language models designed to extend the fully-open and compliant Apertus ecosystem to highly constrained hardware environments.

tools thinking

117 Pulls 4 Tags Updated 3 weeks ago

kat-dev

KAT-Dev-32B and KAT-Dev-72B-Exp are open-source models for software engineering tasks.

92 Pulls 6 Tags Updated 7 months ago

emma-5

Emma-5 è un "mini" Large Language Model decoder-only sperimentale sviluppato da Egomnia S.p.A., progettato per lingua italiana.

54 Pulls 12 Tags Updated 6 days ago