Downloads · 30 days
257
21% of all-time downloads
l3utterfly_-_phi-2-layla-v1-gguf
RichardErkhov/l3utterfly_-_phi-2-layla-v1-gguf
l3utterfly_-_phi-2-layla-v1-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
1.2K
Public
Repo size
32.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf37.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 5, 2024
- Updated
- Oct 5, 2024
- SHA
- fb734efd
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
phi-2-layla-v1 - GGUF
- Model creator: https://huggingface.co/l3utterfly/
- Original model: https://huggingface.co/l3utterfly/phi-2-layla-v1/
| Name | Quant method | Size |
|---|---|---|
| phi-2-layla-v1.Q2_K.gguf | Q2_K | 1.03GB |
| phi-2-layla-v1.IQ3_XS.gguf | IQ3_XS | 1.12GB |
| phi-2-layla-v1.IQ3_S.gguf | IQ3_S | 1.16GB |
| phi-2-layla-v1.Q3_K_S.gguf | Q3_K_S | 1.16GB |
| phi-2-layla-v1.IQ3_M.gguf | IQ3_M | 1.23GB |
| phi-2-layla-v1.Q3_K.gguf | Q3_K | 1.33GB |
| phi-2-layla-v1.Q3_K_M.gguf | Q3_K_M | 1.33GB |
| phi-2-layla-v1.Q3_K_L.gguf | Q3_K_L | 1.47GB |
| phi-2-layla-v1.IQ4_XS.gguf | IQ4_XS | 1.43GB |
| phi-2-layla-v1.Q4_0.gguf | Q4_0 | 1.49GB |
| phi-2-layla-v1.IQ4_NL.gguf | IQ4_NL | 1.5GB |
| phi-2-layla-v1.Q4_K_S.gguf | Q4_K_S | 1.51GB |
| phi-2-layla-v1.Q4_K.gguf | Q4_K | 1.62GB |
| phi-2-layla-v1.Q4_K_M.gguf | Q4_K_M | 1.62GB |
| phi-2-layla-v1.Q4_1.gguf | Q4_1 | 1.65GB |
| phi-2-layla-v1.Q5_0.gguf | Q5_0 | 1.8GB |
| phi-2-layla-v1.Q5_K_S.gguf | Q5_K_S | 1.8GB |
| phi-2-layla-v1.Q5_K.gguf | Q5_K | 1.87GB |
| phi-2-layla-v1.Q5_K_M.gguf | Q5_K_M | 1.87GB |
| phi-2-layla-v1.Q5_1.gguf | Q5_1 | 1.95GB |
| phi-2-layla-v1.Q6_K.gguf | Q6_K | 2.13GB |
| phi-2-layla-v1.Q8_0.gguf | Q8_0 | 2.75GB |
Original model description:
license: mit language:
- en
Model Card
Model Description
Phi-2 fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.
The dataset has been pre-processed by doing the following:
- remove all refusals
- remove any mention of AI assistant
- split any multi-turn dialog generated in the dataset into multi-turn conversations records
- added nfsw generated conversations from the Teatime dataset
- Developed by: l3utterfly
- Funded by: Layla Network
- Model type: Phi-2
- Language(s) (NLP): English
- License: MIT
- Finetuned from model: Phi-2
Uses
Base model used by Layla - the offline personal assistant: https://www.layla-network.ai
Help & support: https://discord.gg/x546YJ6nYC
Prompt:
USER:
ASSISTANT:
- Created
- Oct 5, 2024
- Updated
- Oct 5, 2024