technobyte

llama-3.1-nemotron-70b-instruct

LLM customized by NVIDIA to improve the helpfulness of generated responses #1 on all three automatic alignment benchmarks (verified tab for AlpacaEval 2 LC), edging out strong frontier models such as GPT-4o and Claude 3.5 Sonnet.

1,873 Pulls 1 Tag Updated 5 months ago

mn-12b-starcannon-v2

Very lewd roleplaying model based on Mistral Nemo 12B

1,671 Pulls 3 Tags Updated 6 months ago

Llama-3.3-70B-Abliterated

(for 24 GB) Uncensored L3.3 70B, IQ2_XXS and IQ2_XS version

tools

1,663 Pulls 2 Tags Updated 3 months ago

fimbulvetr-11b-v2.1-16k

🌶️ Uncensored assistant | ⚠️ Warning: very lewd. SOLAR-10.7B | With correct instruction template, works out of the box. Good instruction following.

884 Pulls 2 Tags Updated 6 months ago

arliai-rpmax-12b-v1.1

RPMax is a series of models that are trained on a diverse set of curated creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive.

631 Pulls 2 Tags Updated 6 months ago

c4ai-command-r7b-12-2024

7B model with advanced capabilities optimized for a variety of use cases including reasoning, summarization, question answering, and code.

503 Pulls 1 Tag Updated 3 months ago

Cydonia-24B-v2.1

Updated roleplay finetune of Mistral Small 3 24B by TheDrummer

tools

208 Pulls 1 Tag Updated 5 weeks ago

Cydonia-24B-v2

Roleplay finetune of Mistral Small 3 24B by TheDrummer

tools

182 Pulls 1 Tag Updated 6 weeks ago

Llama-3.1-8B-ArliAI-RPMax-v1.2

174 Pulls 2 Tags Updated 3 months ago

Qwen2.5-7B-VNTL-JP-EN

Japanese to English translation model

53 Pulls 2 Tags Updated 5 weeks ago