Llama can now see and run on your device - welcome Llama 3.2
ā¢
169
Omar Sanseviero
osanseviero
AI & ML interests
Llamas, model merging, massive ASR for data collection, 3D ML, on-device ML, quantization, model judging, ML in browser, healthcare applications, education, intersection of art and ML.š¦
Recent Activity
liked
a Space
3 days ago
Qwen/Qwen2.5-Turbo-1M-Demo
liked
a model
3 days ago
mistralai/Pixtral-Large-Instruct-2411
Articles
Organizations
Posts
19
Post
9455
Diaries of Open Source. Part 15 š¤
šµļøāāļøIdefics 2 is out, a multimodal open-source model with very nice capabilities
Models, demo, and datasets: HuggingFaceM4/idefics2-661d1971b7c50831dd3ce0fe
Blog: https://hf.co/blog/idefics2
š¾Snowflake released snowflake-arctic-embed, a family of powerful small embedding models
Model: Snowflake/snowflake-arctic-embed-m
Blog: https://www.snowflake.com/blog/introducing-snowflake-arctic-embed-snowflakes-state-of-the-art-text-embedding-family-of-models/
āØPile-T5, EleutherAI's T5 model trained on 2T tokens
Blog: https://blog.eleuther.ai/pile-t5/
Models: EleutherAI/pile-t5-65a76a0d0022dd270b385a66
GitHub: https://github.com/EleutherAI/improved-t5
š¤CodeQwen1.5-7B base and chat models. Models trained on 3T tokens strong benchmark results for code generation, editing and SQL
Blog post: https://qwenlm.github.io/blog/codeqwen1.5/
Demo: Qwen/CodeQwen1.5-7b-Chat-demo
Models: Qwen/CodeQwen1.5-7B and Qwen/CodeQwen1.5-7B-Chat
Misc
š¦ DocOwl1.5: Unified Stucture Learning for OCR-free Document Understanding mPLUG/DocOwl
šCerule - a tiny Vision LM model Tensoic/Cerule-v0.1
ChemLLM - a LLM for chemistry and molecule science āļøhttps://hf.co/AI4Chem/ChemLLM-7B-Chat-1.5-DPO
Distil Whisper Large
šNew pdf/OCR datasets with 19 samples pixparse/pdf-document-ocr-datasets-660701430b0346f97c4bc628
š„Gretel AI high quality text-to-sql synthetic dataset gretelai/synthetic_text_to_sql
šµļøāāļøIdefics 2 is out, a multimodal open-source model with very nice capabilities
Models, demo, and datasets: HuggingFaceM4/idefics2-661d1971b7c50831dd3ce0fe
Blog: https://hf.co/blog/idefics2
š¾Snowflake released snowflake-arctic-embed, a family of powerful small embedding models
Model: Snowflake/snowflake-arctic-embed-m
Blog: https://www.snowflake.com/blog/introducing-snowflake-arctic-embed-snowflakes-state-of-the-art-text-embedding-family-of-models/
āØPile-T5, EleutherAI's T5 model trained on 2T tokens
Blog: https://blog.eleuther.ai/pile-t5/
Models: EleutherAI/pile-t5-65a76a0d0022dd270b385a66
GitHub: https://github.com/EleutherAI/improved-t5
š¤CodeQwen1.5-7B base and chat models. Models trained on 3T tokens strong benchmark results for code generation, editing and SQL
Blog post: https://qwenlm.github.io/blog/codeqwen1.5/
Demo: Qwen/CodeQwen1.5-7b-Chat-demo
Models: Qwen/CodeQwen1.5-7B and Qwen/CodeQwen1.5-7B-Chat
Misc
š¦ DocOwl1.5: Unified Stucture Learning for OCR-free Document Understanding mPLUG/DocOwl
šCerule - a tiny Vision LM model Tensoic/Cerule-v0.1
ChemLLM - a LLM for chemistry and molecule science āļøhttps://hf.co/AI4Chem/ChemLLM-7B-Chat-1.5-DPO
Distil Whisper Large
šNew pdf/OCR datasets with 19 samples pixparse/pdf-document-ocr-datasets-660701430b0346f97c4bc628
š„Gretel AI high quality text-to-sql synthetic dataset gretelai/synthetic_text_to_sql
Post
8927
Diaries of Open Source. Part 14 š¤
š„CohereForAI releases Command R+, an open 104B model with:
- Tool usage capabilities
- Specialized in RAGs
- Multilingual
It's one of the first models to surpass GPT-4 in the lmsys arena, check it out!
Model: CohereForAI/c4ai-command-r-plus
Official demo: https://hf.co/spaces/CohereForAI/c4ai-command-r-plus
Quantized: CohereForAI/c4ai-command-r-plus-4bit
šGoogle releases a new version of their Gemma instruct models, with improved quality, nicer to converse, and a fancier RL algorithm. The model is similar to Llama 2 70B in the Chat Arena!
Models: google/gemma-release-65d5efbccdbb8c4202ec078b
Try it out in HuggingChat https://hf.co/chat/models/google/gemma-1.1-7b-it
šŖVoiceCraft, a speech editing and TTS SOTA open model
Paper: VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (2403.16973)
Model: pyp1/VoiceCraft
š»Google released CodeGemma, a family of code generation, completion, and chat models
Blog post: https://hf.co/blog/codegemma
Models: google/codegemma-release-66152ac7b683e2667abdee11
Report: https://storage.googleapis.com/deepmind-media/gemma/codegemma_report.pdf
Misc models:
š¦T-Rex2, a very powerful object detection model for many applications https://github.com/IDEA-Research/T-Rex
š CT-RATE : A 3D dataset paired with text reports ibrahimhamamci/CT-RATE
šOctopus v2: a Gemma-based model trained for Android API - extremely fast, better than Llama+RAG, great results NexaAIDev/Octopus-v2
š„CohereForAI releases Command R+, an open 104B model with:
- Tool usage capabilities
- Specialized in RAGs
- Multilingual
It's one of the first models to surpass GPT-4 in the lmsys arena, check it out!
Model: CohereForAI/c4ai-command-r-plus
Official demo: https://hf.co/spaces/CohereForAI/c4ai-command-r-plus
Quantized: CohereForAI/c4ai-command-r-plus-4bit
šGoogle releases a new version of their Gemma instruct models, with improved quality, nicer to converse, and a fancier RL algorithm. The model is similar to Llama 2 70B in the Chat Arena!
Models: google/gemma-release-65d5efbccdbb8c4202ec078b
Try it out in HuggingChat https://hf.co/chat/models/google/gemma-1.1-7b-it
šŖVoiceCraft, a speech editing and TTS SOTA open model
Paper: VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (2403.16973)
Model: pyp1/VoiceCraft
š»Google released CodeGemma, a family of code generation, completion, and chat models
Blog post: https://hf.co/blog/codegemma
Models: google/codegemma-release-66152ac7b683e2667abdee11
Report: https://storage.googleapis.com/deepmind-media/gemma/codegemma_report.pdf
Misc models:
š¦T-Rex2, a very powerful object detection model for many applications https://github.com/IDEA-Research/T-Rex
š CT-RATE : A 3D dataset paired with text reports ibrahimhamamci/CT-RATE
šOctopus v2: a Gemma-based model trained for Android API - extremely fast, better than Llama+RAG, great results NexaAIDev/Octopus-v2
Collections
13
-
Chain-of-Thought Reasoning Without Prompting
Paper ā¢ 2402.10200 ā¢ Published ā¢ 101 -
Large Language Models Cannot Self-Correct Reasoning Yet
Paper ā¢ 2310.01798 ā¢ Published ā¢ 33 -
Premise Order Matters in Reasoning with Large Language Models
Paper ā¢ 2402.08939 ā¢ Published ā¢ 27 -
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
Paper ā¢ 2402.12875 ā¢ Published ā¢ 13
Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it!
-
Qualitatively characterizing neural network optimization problems
Paper ā¢ 1412.6544 ā¢ Published ā¢ 4 -
Convergent Learning: Do different neural networks learn the same representations?
Paper ā¢ 1511.07543 ā¢ Published ā¢ 2 -
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
Paper ā¢ 1909.11299 ā¢ Published ā¢ 1 -
Model Fusion via Optimal Transport
Paper ā¢ 1910.05653 ā¢ Published ā¢ 1
spaces
178
models
301
osanseviero/qwen2.5_0.5b-instruct-q2_K_test
Updated
osanseviero/qwen2.5-0.5b-instruct-q2_K
Updated
ā¢
10
osanseviero/o-blob-3.2
Updated
ā¢
3
osanseviero/test-in-go7
Updated
osanseviero/test-in-go6
Updated
osanseviero/test-in-go5
Updated
osanseviero/Reflection-Llama-3.1-70B-GGUF
Text Generation
ā¢
Updated
ā¢
138
osanseviero/test-in-go4
Updated
osanseviero/test-in-go3
Updated
osanseviero/test-in-go
Updated
datasets
38
osanseviero/super-fun-llamas
Viewer
ā¢
Updated
ā¢
10
ā¢
48
ā¢
1
osanseviero/fun_llamas
Viewer
ā¢
Updated
ā¢
50
ā¢
46
osanseviero/my-llamas
Viewer
ā¢
Updated
ā¢
100
ā¢
42
osanseviero/bill_summary_us_chunks-similarity
Viewer
ā¢
Updated
ā¢
2k
ā¢
39
osanseviero/bill_summary_us_chunks
Viewer
ā¢
Updated
ā¢
3.45M
ā¢
47
osanseviero/testing_geospatial
Updated
ā¢
38
osanseviero/ag_misclassifications
Viewer
ā¢
Updated
ā¢
200
ā¢
17
osanseviero/test_hacks
Updated
ā¢
4
osanseviero/example_ola
Viewer
ā¢
Updated
ā¢
2
ā¢
4
osanseviero/langchain_hub_test
Viewer
ā¢
Updated
ā¢
1
ā¢
14