All Current GGUF MODELS 32k/128k fp16
leroy Samuel Dyer
LeroyDyer
AI & ML interests
designing Inteligent Models :
.Net Programmer and Artificial inteligent brain designer: Creating the intligence behind machine minds:
The AGI will not be created by a Neural network design But it will be a combination of self improving code and self training neural network : it must be free to roam the internet and pick and choose information for itself and not be given brain dumps which confuse the models anyalitical progres so it right now basically repeating wht it knows but not generating its own formulated answer based on its knowdge base : hence we need code to extract these various data from its mind then reframe the same data then reinsert the knownedge in a fully structured and methodolgy !
hence the model can extract the data from its moind and reorganizes it better than we can ! so self teaching is the first step forwards :
Recent Activity
updated
a model
about 3 hours ago
LeroyDyer/_Spydaz_Web_AI_Pre_train_002
published
a model
about 3 hours ago
LeroyDyer/_Spydaz_Web_AI_Pre_train_002
replied to
burtenshaw's
post
about 4 hours ago
The open LLM leaderboard is completed, retired, dead, ‘ascended to a higher plane’. And in its shadow we have an amazing range of leaderboards built and maintained by the community.
In this post, I just want to list some of those great leaderboards that you should bookmark for staying up to date:
- Chatbot Arena LLM Leaderboard is the first port of call for checking out the best model. It’s not the fastest because humans will need to use the models to get scores, but it’s worth the wait. https://huggingface.co/spaces/lmarena-ai/chatbot-arena-leaderboard
- OpenVLM Leaderboard is great for getting scores on vision language models https://huggingface.co/spaces/opencompass/open_vlm_leaderboard
- Ai2 are doing a great job on RewardBench and I hope they keep it up because reward models are the unsexy workhorse of the field. https://huggingface.co/spaces/allenai/reward-bench
- The GAIA leaderboard is great for evaluating agent applications. https://huggingface.co/spaces/gaia-benchmark/leaderboard
🤩 This seems like such a sustainable way of building for the long term, where rather than leaning on a single company to evaluate all LLMs, we share the load.
Organizations
Collections
23
models
92

LeroyDyer/_Spydaz_Web_AI_Pre_train_002
Text Generation
•
Updated

LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student
Text Generation
•
Updated
•
185
•
1

LeroyDyer/_Spydaz_Web_AI_Mistral_Base
Text Generation
•
Updated
•
10

LeroyDyer/_Spydaz_Web_AI_AGI_R1_Top_Student-Q4_K_M-GGUF
Updated
•
15

LeroyDyer/_Spydaz_Web_AI_TEMP_
Text Generation
•
Updated
•
84

LeroyDyer/_Spydaz_Web_AI_AGI_R1_Math_AdvancedStudent
Text Generation
•
Updated
•
105

LeroyDyer/_Spydaz_Web_AI_AGI_R1_OmG_001
Text Generation
•
Updated
•
35
•
1

LeroyDyer/_Spydaz_Web_AI_AGI_R1_OmG_Coder
Text Generation
•
Updated
•
68

LeroyDyer/_Spydaz_Web_AI_AGI_R1_X2
Text Generation
•
Updated
•
89

LeroyDyer/_Spydaz_Web_AI_AGI_R1_003
Text Generation
•
Updated
•
145
•
1
datasets
66
LeroyDyer/Alignment_Alpaca
Viewer
•
Updated
•
65.3k
•
89
LeroyDyer/AlignmentRP_Alpaca
Viewer
•
Updated
•
53.6k
•
80
LeroyDyer/AlignmentQA
Viewer
•
Updated
•
860k
•
101
LeroyDyer/Text_Guided_Image_Editing_Base64_200
Viewer
•
Updated
•
200
•
67
LeroyDyer/Text_Guided_Image_Editing_Base64
Viewer
•
Updated
•
100
•
57
LeroyDyer/LD50-V-SMILES_QA_to_Base64
Viewer
•
Updated
•
4k
•
55
LeroyDyer/ESOL-V-SMILES_QA_to_Base64
Viewer
•
Updated
•
1.13k
•
69
LeroyDyer/Tox21-V-SMILES_QA_to_Base64
Viewer
•
Updated
•
4k
•
69
LeroyDyer/Spectrogram_Audio_text_to_Base64
Viewer
•
Updated
•
118
•
53
•
2
LeroyDyer/musiccaps_spectrograms_text_to_Base64
Viewer
•
Updated
•
4k
•
86
•
1