EVA-Qwen2.5-32B-v0.2-4bpw-h6-exl2
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste...
Метка: exl2
Llama-3.1-Nemotron-70B-Instruct-HF-4.3bpw-6hb-exl2
Enjoy! Raise an issue if you’d like other BPW levels. Base Model Card Follows: —————————|:—————-|:——|:———-|:——-| You can use...
Llama-3.1-Nemotron-70B-Instruct-HF-8.0bpw-8hb-exl2
Enjoy! Raise an issue if you’d like other BPW levels. Base Model Card Follows: —————————|:—————-|:——|:———-|:——-| You can use...
NeverSleep_Lumimaid-v0.2-123B_exl2_2.75bpw_h8
Wandb: https://wandb.ai/undis95/Lumi-Mistral-Large?nw=nwuserundis95 As some people have told us our models are sloppy, Ikari decided to say fuck it...
L3-8B-Stheno-v3.3-32K-8.0bpw-h8-exl2
Trained with compute from Backyard.ai | Thanks to them and @dynafire for helping me out. Relevant Axolotl Configurations:...
dolphin-2.9.1-llama-3-70b-6.0bpw-exl2
This model fits comfortably within 72gb of VRAM with 32k context. Enjoy! Feel free to reach out for...
Maiden-Unquirked-20B-6.0bpw-h6-exl2
This is a merge of pre-trained language models created using mergekit. This model was merged using the DARE...
EtherealRainbow-v0.2-8B_EXL2_8BPW
Ethereal Rainbow is an 8B parameter merge of various Llama3-based finetunes created using mergekit. The purpose of Ethereal...
Typhon-Mixtral-v1-3.75bpw-h6-exl2
Exllamav2 3.75bpw quantization of Typhon-Mixtral-v1 from Sao10K, quantized with default calibration dataset. > [!IMPORTANT] >This bpw is the...
Codestral-22B-v0.1-exl2_8.0bpw
Codestrall-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as...