Downloads · 30 days
6
1% of all-time downloads
Fizzarolli_-_L3.1-70b-glitz-v0.2-gguf
RichardErkhov/Fizzarolli_-_L3.1-70b-glitz-v0.2-gguf
Fizzarolli_-_L3.1-70b-glitz-v0.2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
531
Public
Repo size
799 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf926 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 7, 2024
- Updated
- Aug 8, 2024
- SHA
- 6e1765b9
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3.1-70b-glitz-v0.2 - GGUF
- Model creator: https://huggingface.co/Fizzarolli/
- Original model: https://huggingface.co/Fizzarolli/L3.1-70b-glitz-v0.2/
| Name | Quant method | Size |
|---|---|---|
| L3.1-70b-glitz-v0.2.Q2_K.gguf | Q2_K | 24.56GB |
| L3.1-70b-glitz-v0.2.IQ3_XS.gguf | IQ3_XS | 27.29GB |
| L3.1-70b-glitz-v0.2.IQ3_S.gguf | IQ3_S | 28.79GB |
| L3.1-70b-glitz-v0.2.Q3_K_S.gguf | Q3_K_S | 28.79GB |
| L3.1-70b-glitz-v0.2.IQ3_M.gguf | IQ3_M | 29.74GB |
| L3.1-70b-glitz-v0.2.Q3_K.gguf | Q3_K | 31.91GB |
| L3.1-70b-glitz-v0.2.Q3_K_M.gguf | Q3_K_M | 31.91GB |
| L3.1-70b-glitz-v0.2.Q3_K_L.gguf | Q3_K_L | 34.59GB |
| L3.1-70b-glitz-v0.2.IQ4_XS.gguf | IQ4_XS | 35.64GB |
| L3.1-70b-glitz-v0.2.Q4_0.gguf | Q4_0 | 37.22GB |
| L3.1-70b-glitz-v0.2.IQ4_NL.gguf | IQ4_NL | 37.58GB |
| L3.1-70b-glitz-v0.2.Q4_K_S.gguf | Q4_K_S | 37.58GB |
| L3.1-70b-glitz-v0.2.Q4_K.gguf | Q4_K | 39.6GB |
| L3.1-70b-glitz-v0.2.Q4_K_M.gguf | Q4_K_M | 39.6GB |
| L3.1-70b-glitz-v0.2.Q4_1.gguf | Q4_1 | 41.27GB |
| L3.1-70b-glitz-v0.2.Q5_0.gguf | Q5_0 | 45.32GB |
| L3.1-70b-glitz-v0.2.Q5_K_S.gguf | Q5_K_S | 45.32GB |
| L3.1-70b-glitz-v0.2.Q5_K.gguf | Q5_K | 46.52GB |
| L3.1-70b-glitz-v0.2.Q5_K_M.gguf | Q5_K_M | 46.52GB |
| L3.1-70b-glitz-v0.2.Q5_1.gguf | Q5_1 | 49.36GB |
| L3.1-70b-glitz-v0.2.Q6_K.gguf | Q6_K | 53.91GB |
| L3.1-70b-glitz-v0.2.Q8_0.gguf | Q8_0 | 69.83GB |
Original model description:
license: llama3.1 datasets:
- secret/sauce library_name: transformers tags:
- conversational
- roleplay
<style> img { margin-bottom: 0; } </style>
Glitz v0.2 ✨💅
<small>art by spindlehorse toons. i do not own this image. all credit goes to them!</small>
compute sponsored by ShuttleAI
details
this is an experimental l3.1 70b finetuning run... that crashed midway through. however, the results are still interesting, so i wanted to publish them :3
prompting
use l3 instruct. not writing an example, almost everything supports it by now and i don't feel like remembering the stupid tags
datasets
a mix of publicly available claude synth data in various domains, mostly. also systemchat but i refuse to credit cognitive computations for anything decent so forget i said it
- Created
- Aug 7, 2024
- Updated
- Aug 8, 2024