Step-3.5-Flash Chatbot
š
43
Run interactive Streamlit apps directly in your browser
DedeProGames PRO
DedeProGames
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
liked
a Space about 4 hours ago
stepfun-ai/Step-3.5-Flash reacted
to
their post with š about 4 hours ago
Introducing GRM Family, a family of fine-tuned small models from the Qwen2.5 family for Long Cot and General Reasoning and Agentic Tasks.
GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
https://huggingface.co/OrionLLM/GRM-7b
https://huggingface.co/OrionLLM/GRM-1.5b new activity
about 6 hours ago
huggingface/InferenceSupport:zai-org/GLM-4.1V-9B-Thinking Organizations
liked a Space about 4 hours ago
reacted to their post with š about 4 hours ago
Post
249
Introducing GRM Family, a family of fine-tuned small models from the Qwen2.5 family for Long Cot and General Reasoning and Agentic Tasks.
GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
OrionLLM/GRM-7b
OrionLLM/GRM-1.5b
GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
OrionLLM/GRM-7b
OrionLLM/GRM-1.5b
zai-org/GLM-4.1V-9B-Thinking
#8706 opened about 6 hours ago
by
DedeProGames
updated 3 models about 6 hours ago
Request for GRM Family Benchmark Evaluation
#3 opened about 6 hours ago
by
DedeProGames
Evaluate GRM Family
#2 opened about 6 hours ago
by
DedeProGames
liked a model about 6 hours ago
liked a Space about 6 hours ago
upvoted a paper about 10 hours ago
reacted to W8Yi's post with š about 10 hours ago
Post
2586
I built a **TCGA WSI feature dataset using UNI2-h**.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
ā¢ **All detected tissue tiles are encoded** (not a sampled subset)
ā¢ **Features can be downloaded per slide** instead of large ZIP archives
ā¢ **QC overlay images** are provided for visual inspection
ā¢ **UNI2-h 1536-D tile embeddings** stored in H5 format
ā¢ Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
Hope this helps others working on computational pathology and TCGA WSI research.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
ā¢ **All detected tissue tiles are encoded** (not a sampled subset)
ā¢ **Features can be downloaded per slide** instead of large ZIP archives
ā¢ **QC overlay images** are provided for visual inspection
ā¢ **UNI2-h 1536-D tile embeddings** stored in H5 format
ā¢ Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
TCGA-HNSC/
features/*.h5
vis/*__overlay.pngHope this helps others working on computational pathology and TCGA WSI research.
posted an
update about 10 hours ago
Post
249
Introducing GRM Family, a family of fine-tuned small models from the Qwen2.5 family for Long Cot and General Reasoning and Agentic Tasks.
GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
OrionLLM/GRM-7b
OrionLLM/GRM-1.5b
GRM is available in 7b and 1.5b parameter sizes, these models being significantly relevant for complex tasks or local inference agents.
OrionLLM/GRM-7b
OrionLLM/GRM-1.5b
liked a Space about 12 hours ago
updated a Space about 18 hours ago
OrionLLM/GRM-1.5b
š š„ 1
#8692 opened 1 day ago
by
DedeProGames
liked a Space 1 day ago
OrionLLM/GRM-7b
š§ š„ 1
#8688 opened 1 day ago
by
DedeProGames
Tesslate/OmniCoder-9B
#8687 opened 1 day ago
by
DedeProGames
reacted to AtAndDev's post with š 1 day ago
Post
652
Qwen 3 Coder is a personal attack to k2, and I love it.
It achieves near SOTA on LCB while not having reasoning.
Finally people are understanding that reasoning isnt necessary for high benches...
Qwen ftw!
DECENTRALIZE DECENTRALIZE DECENTRALIZE
It achieves near SOTA on LCB while not having reasoning.
Finally people are understanding that reasoning isnt necessary for high benches...
Qwen ftw!
DECENTRALIZE DECENTRALIZE DECENTRALIZE