Hermes-Kimiko-13B-f16
This is a model merge of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b + https://huggingface.co/nRuaif/Kimiko_13B) Lora merge was done at full weight (1:1 ratio)...
Метка: llama-2
Vigogne-2-7B-Instruct-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
Vigogne-2-13B-Instruct-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
Llama-2-7b-chat-hf-sharded-bf16-5GB
This is a sharded version of Meta’s Llama 2 chat 7b model, specifically the hugging face version. Shards...
Nous-Hermes-Llama2-13b-Storywriter
This is a model merge of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b + https://huggingface.co/Blackroot/Llama-2-13B-Storywriter-LORA A brief warning, no alignment or attempts of any...
Nous-Hermes-Llama2-13b-GPTQ
Compute provided by our project sponsor Redmond AI, thank you! Follow RedmondAI on Twitter @RedmondAI. Nous-Hermes-Llama2-13b is a...
Llama-2-7b-hf
The weight file is split into chunks with a size of 405MB for convenient and fast parallel downloads...
llama-2-7b-chat-guanaco-hf-4bit
— BaseModel: Meta’s Llama 2 7B chat hf. — Dataset: timdettmers/openassistant-guanaco. We are unlocking the power of large...
ct2fast-Llama-2-7b-hf
Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU. Checkpoint compatible...
layerskip-codellama-34B
Модель Code Llama 34B постоянно предварительно обучается с помощью LayerSkip, как показано в разделе «Пропуск слоя: включение раннего...