-
nous-hermes-2-solar-10.7b
Nous Hermes 2 Fine-tune of SOLAR 10.7B
1,401 Pulls 4 Tags Updated 10 months ago
-
nous-capybara
Nous-Capybara-34B V1.9 in select quantizations
34b905 Pulls 4 Tags Updated 12 months ago
-
wizardlm-uncensored
WizardLM-33B-V1.0-Uncensored
821 Pulls 2 Tags Updated 11 months ago
-
dragon-mistral-v0
Mistral model fine-tuned for RAG by llmware
7b497 Pulls 5 Tags Updated 11 months ago
-
bagel-dpo
237 Pulls 4 Tags Updated 10 months ago
-
codellama
Codelama with 16k context unlocked in modelfile
217 Pulls 2 Tags Updated 11 months ago
-
capybara-tess-yi-34b-200k-dare-ties
Quantized versions of a model merge between nous-capybara and tess-yi.
205 Pulls 3 Tags Updated 11 months ago
-
dolphin-2.2-yi
Dolphin 2.2 fine tune of Yi 34b base.
34b203 Pulls 4 Tags Updated 12 months ago
-
openhermes-2.5-neural-chat-v3-3-slerp
Merge of OpenHermes-2.5 and NeuralChat-3.3
185 Pulls 4 Tags Updated 11 months ago
-
dragon-yi-v0
Yi model fine-tuned for RAG by llmware
6b156 Pulls 5 Tags Updated 11 months ago
-
capytessborosyi-34b-200k-dare-ties
q3_K_M and q4_K_M configured with 10k context
155 Pulls 3 Tags Updated 11 months ago
-
neuralbeagle14
quantized versions of mlabonne/NeuralBeagle14-7B
130 Pulls 4 Tags Updated 9 months ago
-
airoboros-m-7b-3.1.2
124 Pulls 2 Tags Updated 12 months ago
-
openchat
q4_k_m quantization only. Now using 8k context size
83 Pulls 1 Tag Updated 12 months ago
-
nous-genstruct
Genstruct 7B is an instruction-generation model, designed to create valid instructions given a raw text corpus.
78 Pulls 4 Tags Updated 8 months ago
-
beyonder-4x7b
59 Pulls 4 Tags Updated 10 months ago
-
omnibeagle
Omnibeagel with 4K context
51 Pulls 5 Tags Updated 8 months ago
-
free_sydney_v2_13b
8 Pulls 1 Tag Updated 12 months ago