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
Language(s) (NLP): English
License: MIT
Finetuned from model: Phi-2
Repository: localaiLicense: mit
phi-2-chat:Q8_0
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
Language(s) (NLP): English
License: MIT
Finetuned from model: Phi-2
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
Language(s) (NLP): English
License: MIT
Finetuned from model: Phi-2
Repository: localaiLicense: mit
phi-2-chat
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
Language(s) (NLP): English
License: MIT
Finetuned from model: Phi-2
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This model is designed for general code synthesis and understanding.
Repository: localaiLicense: llama2
codellama-7b
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This model is designed for general code synthesis and understanding.
LeetCodeWizard is a coding large language model specifically trained to solve and explain Leetcode (or any) programming problems.
This model is a fine-tuned version of the WizardCoder-Python-7B with a dataset of Leetcode problems\
Model capabilities:
It should be able to solve most of the problems found at Leetcode and even pass the sample interviews they offer on the site.
It can write both the code and the explanations for the solutions.
Repository: localaiLicense: llama2
leetcodewizard_7b_v1.1-i1
LeetCodeWizard is a coding large language model specifically trained to solve and explain Leetcode (or any) programming problems.
This model is a fine-tuned version of the WizardCoder-Python-7B with a dataset of Leetcode problems\
Model capabilities:
It should be able to solve most of the problems found at Leetcode and even pass the sample interviews they offer on the site.
It can write both the code and the explanations for the solutions.