Nous Hermes 2 Fine-tune of SOLAR 10.7B

1,343  Pulls 4 Tags Updated  6 months ago

Nous-Capybara-34B V1.9 in select quantizations

794  Pulls 4 Tags Updated  9 months ago

WizardLM-33B-V1.0-Uncensored

444  Pulls 2 Tags Updated  10 months ago

Mistral model fine-tuned for RAG by llmware

414  Pulls 5 Tags Updated  9 months ago

234  Pulls 4 Tags Updated  8 months ago

Quantized versions of a model merge between nous-capybara and tess-yi.

197  Pulls 3 Tags Updated  9 months ago

Dolphin 2.2 fine tune of Yi 34b base.

178  Pulls 4 Tags Updated  10 months ago

Merge of OpenHermes-2.5 and NeuralChat-3.3

175  Pulls 4 Tags Updated  9 months ago

Codelama with 16k context unlocked in modelfile

171  Pulls 2 Tags Updated  10 months ago

Yi model fine-tuned for RAG by llmware

151  Pulls 5 Tags Updated  9 months ago

q3_K_M and q4_K_M configured with 10k context

150  Pulls 3 Tags Updated  9 months ago

quantized versions of mlabonne/NeuralBeagle14-7B

119  Pulls 4 Tags Updated  7 months ago

100  Pulls 2 Tags Updated  10 months ago

q4_k_m quantization only. Now using 8k context size

79  Pulls 1 Tag Updated  10 months ago

Genstruct 7B is an instruction-generation model, designed to create valid instructions given a raw text corpus.

73  Pulls 4 Tags Updated  6 months ago

56  Pulls 4 Tags Updated  8 months ago

Omnibeagel with 4K context

51  Pulls 5 Tags Updated  6 months ago

7  Pulls 1 Tag Updated  10 months ago