Ausboss
Rank:Average Model Cost: $0.0000
Number of Runs: 3,716
Models by this creator
llama-30b-supercot
llama-30b-supercot
Merge of huggyllama/llama-30b + kaiokendev/SuperCOT-LoRA Supercot was trained to work with langchain prompting. Load up locally in my custom LLM notebook that uses the Oobabooga modules to load up models: https://github.com/ausboss/Local-LLM-Langchain Then you can add cells from of these other notebooks for testing: https://github.com/gkamradt/langchain-tutorials From Koikendev Lora page Compatibility This LoRA is compatible with any 7B, 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins Prompting You should prompt the LoRA the same way you would prompt Alpaca or Alpacino: Remember that with lower parameter sizes, the structure of the prompt becomes more important. The same prompt worded differently can give wildly different answers. Consider using the following suggestion suffixes to improve output quality: "Think through this step by step" "Let's think about this logically" "Explain your reasoning" "Provide details to support your answer" "Compare and contrast your answer with alternatives" Coming Soon Tweet fix for 13B and 7B - lower model sizes seem to be extremely sensitive to hashtags at the end of training data responses, especially at longer cutoffs
$-/run
2.8K
Huggingface
llama-13b-supercot
llama-13b-supercot
This model is a merge of LLAMA-13b and SuperCOT LoRA huggyllama/llama-13b + kaiokendev/SuperCOT-LoRA/13b/gpu/cutoff-2048
$-/run
430
Huggingface
llama-13b-supercot-4bit-128g
$-/run
250
Huggingface
llama-30b-SuperHOT-4bit
llama-30b-SuperHOT-4bit
Merge of SuperHOT-LoRA-prototype and llama-30b Llama30B-SuperHOT-4bit-128g.safetensors Quantization: Llama30B-SuperHOT-4bit.safetensors Quantization: From the SuperHot Page: Prototypes for SuperHOT No guarantees for output quality, simply uploading what I have so others can play around with it. Not even sure if the rank in cutoff-8192 is correct (think it should be 10 maybe.. can't remember) All prototypes are extremely early epochs (sub 0.5) Model/Training All trained with Flash Attention with conversation sequence lengths ranging from 8K to 16K tokens (No Alibi unless otherwise mentioned) All trained on LLaMa 13B 4-bit (no groupsize) (Personally, I like the 8K cutoff version better, so I would say start with that one) Data A combination of various datasets and cleaned logs converted into datasets including but not limited to: Bluemoon Fanbased Roleplaying Guild Community-sourced outputs Dan's PocketDoc/RUCAIBox-Story-Generation-Alpaca IlyaGusev/gpt_roleplay_realm others Bias SuperHOT is a fiction-focused model. No alignment has been performed on the training data. Be mindful that this model may output harmful, violent, or otherwise problematic content Format Any format should work with such early checkpoints. However the training data is entirely in the following format: By "any other miscellaneous data", it means you should be able to put any additional metadata for the story or characters. I.e., Again, format does not hold such a large weight on these early checkpoints. I have found success with the following setup for an RPG-like experience. Just play around with the format and see what works:
$-/run
87
Huggingface
llama7b-wizardlm-unfiltered-4bit-128g
llama7b-wizardlm-unfiltered-4bit-128g
Lora fine tune trained on this dataset CUDA_VISIBLE_DEVICES=0 python llama.py model c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors
$-/run
51
Huggingface
llama7b-wizardlm-unfiltered
$-/run
29
Huggingface
llama-30b-supercot-4bit
$-/run
18
Huggingface
LunarLander
LunarLander
PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. Usage (with Stable-baselines3) TODO: Add your code
$-/run
1
Huggingface
llama-30b-superhotcot.ggmlv3.q4_0
llama-30b-superhotcot.ggmlv3.q4_0
SuperCot + SuperHOT This is my first time doing a GGML. It might suck. Two possible prompting methods:
$-/run
0
Huggingface