prism-ml/Bonsai-8B-gguf
Text Generation ā¢ 8B ā¢ Updated ā¢ 13.8k ā¢ 303
Gabriel
gacosta26
AI & ML interests
None yet
Recent Activity
liked a model about 8 hours ago
prism-ml/Bonsai-8B-gguf upvoted a collection about 8 hours ago
Bonsai liked a model about 18 hours ago
nvidia/Phi-4-multimodal-instruct-NVFP4Organizations
None yet
liked a
model about 8 hours ago
upvoted a collection about 8 hours ago
liked a
model about 18 hours ago
liked 2
models 1 day ago
reactedto DedeProGames's post with š„š„ 1 day ago
Post
1351
š„ GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
š¤ Model: OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
š Chat with GRM:
DedeProGames/GRM2-Chat
š Download official GGUFs: OrionLLM/GRM2-3b-GGUF
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
š¤ Model: OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.
š Chat with GRM:
DedeProGames/GRM2-Chat
š Download official GGUFs: OrionLLM/GRM2-3b-GGUF
upvoted a collection 1 day ago
liked a
model 2 days ago
upvoted a collection 2 days ago
reactedto danielhanchen's post with š„ 2 days ago
Post
2302
A new way to use Unsloth.
Coming soon...
Coming soon...
liked a
model 2 days ago
liked 5
models 5 days ago
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
Text Generation ā¢ 9B ā¢ Updated ā¢ 238k ā¢ 222
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Text Generation ā¢ 10B ā¢ Updated ā¢ 99.1k ā¢ 52
Jackrong/Qwen3.5-9B-Neo-GGUF
Text Generation ā¢ 9B ā¢ Updated ā¢ 6.12k ā¢ 12
ibm-granite/granite-4.0-3b-vision
Image-Text-to-Text ā¢ 4B ā¢ Updated ā¢ 2.38k ā¢ 71
LiquidAI/LFM2-8B-A1B
Text Generation ā¢ 8B ā¢ Updated ā¢ 48k ā¢ 343
liked a
model 7 days ago
reactedto karstenskyt's post with š„ 7 days ago
Post
2259
š šš®šš»š°šµš¶š»š“ ššµš² šš/š š šŖš¼šæšøš³š¹š¼šš šš®ššµšÆš¼š®šæš±
Now that our Taipy architecture is humming along on Hugging Face Spaces, we just shipped the most complex feature of the (ššŖšØš©šµ! šš¶š¹š¶š³šŗ!) šš¢š¬š¦š©š°š¶š“š¦ to date: the šš/š š šŖš¼šæšøš³š¹š¼šš šš®ššµšÆš¼š®šæš±.
Managing 16 different machine learning pipelines (from Expected Goals to Space Creation) across Databricks Serverless and HF Jobs is a logistical challenge. To solve this, we built a dynamic operations center (the 13th page in our app).
It features:
Ā Ā ā¢ šš» š¶š»šš²šæš®š°šš¶šš² š±š²š½š²š»š±š²š»š°š ššš: Powered by Cytoscape.js, it visually maps exactly how our models and data grids feed into each other.
Ā Ā ā¢ š„š²š®š¹-šš¶šŗš² šŗš¼š»š¶šš¼šæš¶š»š“: Tracks run volumes and data freshness SLAs across the entire platform.
Ā Ā ā¢ š šÆ-šš¶š²šæ šµššÆšæš¶š± š°š¼šš š²š»š“š¶š»š²: Merges "cold" Databricks billing data with "warm/hot" live HF Jobs estimates to give a unified view of pipeline expenses.
Check out the live interactive graph here:
luxury-lakehouse/soccer-analytics-app
Now that our Taipy architecture is humming along on Hugging Face Spaces, we just shipped the most complex feature of the (ššŖšØš©šµ! šš¶š¹š¶š³šŗ!) šš¢š¬š¦š©š°š¶š“š¦ to date: the šš/š š šŖš¼šæšøš³š¹š¼šš šš®ššµšÆš¼š®šæš±.
Managing 16 different machine learning pipelines (from Expected Goals to Space Creation) across Databricks Serverless and HF Jobs is a logistical challenge. To solve this, we built a dynamic operations center (the 13th page in our app).
It features:
Ā Ā ā¢ šš» š¶š»šš²šæš®š°šš¶šš² š±š²š½š²š»š±š²š»š°š ššš: Powered by Cytoscape.js, it visually maps exactly how our models and data grids feed into each other.
Ā Ā ā¢ š„š²š®š¹-šš¶šŗš² šŗš¼š»š¶šš¼šæš¶š»š“: Tracks run volumes and data freshness SLAs across the entire platform.
Ā Ā ā¢ š šÆ-šš¶š²šæ šµššÆšæš¶š± š°š¼šš š²š»š“š¶š»š²: Merges "cold" Databricks billing data with "warm/hot" live HF Jobs estimates to give a unified view of pipeline expenses.
Check out the live interactive graph here:
luxury-lakehouse/soccer-analytics-app
High token count after code implementatio
#2 opened 7 days ago
by gacosta26