ExllamaV2 version of the model created by IkariDev and Undi
Original Model https://huggingface.co/NeverSleep/Echidna-13b-v0.2
Requires ExllamaV2, which is being developed by turboderp https://github.com/turboderp/exllamav2 under an MIT license.
This model is a collab between IkariDev and Undi!
Echidna v0.2 model. Use Alpaca format. Suitable for RP, ERP and general stuff.
Echidna v0.3 will be a heavily refined version of this model/recipe!
This model seems to be pretty sensitive to your generation settings, experiment until you've found your settings.
[Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
<!-- description start -->
Description
<!-- Recommended settings - contributed by localfultonextractor -->
This repo contains FP16 files of Echidna-13b-v0.2.
<!-- GGUF - By TheBloke-->
<!-- GPTQ - By TheBloke-->
<!-- exl2 - by waldie-->
<!-- AWQ - By TheBloke-->
<!-- fp16 - by IkariDev+Undi95-->
GGUF - by IkariDev and Undi <!-- OLD(GGUF - by IkariDev+Undi95)-->
Ratings:
Note: We have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!
No ratings yet!
If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
<!-- description end --> <!-- description start -->
Models+loras used and recipe
- Xwin-LM/Xwin-LM-13B-V0.2
- IkariDev/Athena-v3
- Heralax/Cat-0.5
- Undi95/PsyMedRP-v1-13B
- cgato/Thespis-13b-v0.4
- KoboldAI/LLaMA2-13B-Tiefighter
- Heralax/Augmental-13b-two-epochs
- Sao10K/SthenoWriter2.1-L2-13B
- Undi95/Storytelling-v2.1-13B-lora
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT <!-- description end --> <!-- prompt-template start -->
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Others
Undi: If you want to support me, you can here.
IkariDev: Visit my retro/neocities style website please kek