GGUF-IQ-Imatrix quants for TheSkullery/llama-3-cat-8b-instruct-v1.
Imatrix data generated from the FP16-GGUF and conversions from the BF16-GGUF.
Author:
"The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion in given scenes."
I apologize for disrupting your experience.
My upload speeds have been cooked and unstable lately.
If you want and you are able to...
You can support my various endeavors by clicking here (Ko-fi).
Relevant:
These quants have been done after the fixes from llama.cpp/pull/6920 have been merged.
Use KoboldCpp version 1.64 or higher, make sure you're up-to-date.
Compatible SillyTavern presets recommended by the authors are hosted in the repository files or here (Virt's Roleplay Presets - my personal recommendation).
Use the latest version of KoboldCpp. Use the provided presets for testing.
Feedback and support for the Authors is always welcome.
If there are any issues or questions let me know.
For 8GB VRAM GPUs, I recommend the Q4_K_M-imat (4.89 BPW) quant for up to 12288 context sizes.
Original model information:
Presented by:
70b variant of the model (Trained by Dr. Kal'tsit, Posted by Turboderp), Please check it out!
Cat-llama3-instruct is a llama 3 8b finetuned model focusing on system prompt fidelity, helpfulness and character engagement. The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion (Role Play) in given scenes.
Huggingface dataset containing instruction-response pairs was systematically pulled. A GPT model was trained on high quality and helpful responses exclusively to serve as a standard model.
(Fig1. Huggingface dataset population distribution and filtration for each component)
The dataset was further filtered for length and COT responses:
(Fig 2. COT responses are all >50 tokens single turn)
Health-related data was also pulled from Chat Doctor, favoring detailed and step-by-step diagnosis:
(Fig 3. Health related tasks are all >100 tokens, peaking at 450 tokens single turn)
1*a100 for 6 days, 4 epochs
<|begin_of_text|>Below is a conversation between an user and an AI assistant. The ai assistant gives response regarding user's questions. USER: user: Given the task definition and input, reply with output. In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.Question: What type of diseases in humans are caused by protozoa? Answer: protist diseases ASSISTANT: AI: Task Explanation: In this task, you are asked to create a sentence using the given question and the provided answer. The sentence you create should include the information from both the question and the answer in a concise and coherent manner. Guidelines:
- Read the given question and answer carefully.
- Combine the information from the question and answer to create a new sentence.
- Make sure your new sentence contains both the question's information and the answer provided.
- Check your sentence for proper grammar and punctuation. Steps to find the answer:
- Read the question: "What type of diseases in humans are caused by protozoa?"
- Read the answer: "protist diseases"
- Combine the information from the question and answer to create a new sentence: "In humans, protist diseases are caused by protozoa."
Double-check the sentence for proper grammar and punctuation, and make necessary adjustments if needed. Final Output: In humans, protist diseases are caused by protozoa.< / s ><|end_of_text|>
The model does COT in grey, calculated response in black; note that this behaviour is done through system card instruction to showcase the systemcard fidelity, it is not fine tuned into the model.
(Fig 4. Showcasing model doing COT to solve difficult tasks, extend and enrich its own answers)
