Hugging Face's logo

GEM benchmark

https://gem-benchmark.com
Activity Feed Request to join this org

AI & ML interests

We develop infrastructure for the evaluation of generated text.

Recent Activity

KrystalanΒ  authored a paper 13 days ago
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
fladhakΒ  authored a paper 23 days ago
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
gentaiscoolΒ  authored a paper 27 days ago
Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision
View all activity

GEM's activity

Sri-Vigneshwar-DJΒ 
posted an update 3 days ago
view post
Post
549
Checkout phi-4 from Microsoft, dropped a day ago... If you ❀️ the Phi series, then here is the GGUF - Sri-Vigneshwar-DJ/phi-4-GGUF. phi-4 is a 14B highly efficient open LLM that beats much larger models at math and reasoning - check out evaluations on the Open LLM.

Technical paper - https://arxiv.org/pdf/2412.08905 ; The Data Synthesis approach is interesting
prithivMLmodsΒ 
posted an update 3 days ago
view post
Post
2420
200+ f{πŸ€—} on Stranger Zone! [ https://huggingface.co/strangerzonehf ]

❀️‍πŸ”₯Stranger Zone's MidJourney Mix Model Adapter is trending on the Very Model Page, with over 45,000+ downloads. Additionally, the Super Realism Model Adapter has over 52,000+ downloads, remains the top two adapter on Stranger Zone!
strangerzonehf/Flux-Midjourney-Mix2-LoRA, strangerzonehf/Flux-Super-Realism-LoRA

πŸ‘½Try Demo: prithivMLmods/FLUX-LoRA-DLC

πŸ“¦Most Recent Adapters to Check Out :
+ Ctoon : strangerzonehf/Ctoon-Plus-Plus
+ Cardboard : strangerzonehf/Flux-Cardboard-Art-LoRA
+ Claude Art : strangerzonehf/Flux-Claude-Art
+ Flay Lay : strangerzonehf/Flux-FlatLay-LoRA
+ Smiley Portrait : strangerzonehf/Flux-Smiley-Portrait-LoRA

πŸ€—Thanks for Community & OPEN SOURCEEE !!
  • 6 replies
Β·
albertvillanovaΒ 
posted an update 6 days ago
Sri-Vigneshwar-DJΒ 
posted an update 6 days ago
view post
Post
2011
Just sharing a thought: I started using DeepSeek V3 a lot, and an idea struck me about agents "orchestrating during inference" on a test-time compute model like DeepSeek V3 or the O1 series.

Agents (Instruction + Function Calls + Memory) execute during inference, and based on the output decision, a decision is made to scale the time to reason or perform other tasks.
prithivMLmodsΒ 
posted an update 7 days ago
view post
Post
5445
Reasoning SmolLM2 πŸš€

🎯Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.

πŸ”₯Blog : https://huggingface.co/blog/prithivMLmods/smollm2-ft

πŸ”Ό Models :
+ SmolLM2-CoT-360M : prithivMLmods/SmolLM2-CoT-360M
+ Reasoning-SmolLM2-135M : prithivMLmods/Reasoning-SmolLM2-135M
+ SmolLM2-CoT-360M-GGUF : prithivMLmods/SmolLM2-CoT-360M-GGUF

🀠 Other Details :
+ Demo : prithivMLmods/SmolLM2-CoT-360M
+ Fine-tune nB : prithivMLmods/SmolLM2-CoT-360M
lewtunΒ 
posted an update 7 days ago
view post
Post
3178
I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!

https://x.com/casper_hansen_/status/1875872309996855343

Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!

[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime
Sri-Vigneshwar-DJΒ 
posted an update 8 days ago
view post
Post
2314
Combining smolagents with Anthropic’s best practices simplifies building powerful AI agents:

1. Code-Based Agents: Write actions as Python code, reducing steps by 30%.
2. Prompt Chaining: Break tasks into sequential subtasks with validation gates.
3. Routing: Classify inputs and direct them to specialized handlers.
4. Fallback: Handle tasks even if classification fails.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/building-effective-agents-with-anthropics-best-pra
prithivMLmodsΒ 
posted an update 12 days ago
view post
Post
3822
Triangulum Catalogued πŸ”₯πŸ’«

🎯Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.

+ Triangulum-10B : prithivMLmods/Triangulum-10B
+ Quants : prithivMLmods/Triangulum-10B-GGUF

+ Triangulum-5B : prithivMLmods/Triangulum-5B
+ Quants : prithivMLmods/Triangulum-5B-GGUF

+ Triangulum-1B : prithivMLmods/Triangulum-1B
+ Quants : prithivMLmods/Triangulum-1B-GGUF
Β·
KrystalanΒ 
authored a paper 13 days ago
lewtunΒ 
posted an update 14 days ago
view post
Post
2074
This paper ( HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs (2412.18925)) has a really interesting recipe for inducing o1-like behaviour in Llama models:

* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting.
* Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases)
* Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1
* Use the resulting data for SFT & RL
* Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.

Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
  • 1 reply
Β·
prithivMLmodsΒ 
posted an update 21 days ago
fladhakΒ 
authored a paper 23 days ago
prithivMLmodsΒ 
posted an update 24 days ago
view post
Post
2527
Qwen2VL Models: Vision and Language Processing πŸ‰

πŸ“FT; [ Latex OCR, Math Parsing, Text Analogy OCRTest ]

Colab Demo: prithivMLmods/Qwen2-VL-OCR-2B-Instruct

❄️Demo : prithivMLmods/Qwen2-VL-2B . The demo includes the Qwen2VL 2B Base Model.

🎯The space handles documenting content from the input image along with standardized plain text. It includes adjustment tools with over 30 font styles, file formatting support for PDF and DOCX, textual alignments, font size adjustments, and line spacing modifications.

πŸ“„PDFs are rendered using the ReportLab software library toolkit.

🧡Models :
+ prithivMLmods/Qwen2-VL-OCR-2B-Instruct
+ prithivMLmods/Qwen2-VL-Ocrtest-2B-Instruct
+ prithivMLmods/Qwen2-VL-Math-Prase-2B-Instruct

πŸš€Sample Document :
+ https://drive.google.com/file/d/1Hfqqzq4Xc-3eTjbz-jcQY84V5E1YM71E/view?usp=sharing

πŸ“¦Collection :
+ prithivMLmods/vision-language-models-67639f790e806e1f9799979f

.
.
.
@prithivMLmods πŸ€—
  • 1 reply
Β·
prithivMLmodsΒ 
posted an update 25 days ago
view post
Post
3274
πŸŽ„ Here Before - XmasπŸŽ…βœ¨

πŸ§‘πŸ»β€πŸŽ„Models
+ [ Xmas 2D Illustration ] : strangerzonehf/Flux-Xmas-Illustration-LoRA
+ [ Xmas 3D Art ] : strangerzonehf/Flux-Xmas-3D-LoRA
+ [ Xmas Chocolate ] : strangerzonehf/Flux-Xmas-Chocolate-LoRA
+ [ Xmas Isometric Kit ] : strangerzonehf/Flux-Xmas-Isometric-Kit-LoRA
+ [ Xmas Realpix ] : strangerzonehf/Flux-Xmas-Realpix-LoRA
+ [ Xmas Anime ] : strangerzonehf/Flux-Anime-Xmas-LoRA

❄️Collections
+ [ Xmas Art ] : strangerzonehf/christmas-pack-6758b199487adafaddb68f82
+ [ Stranger Zone Collection ] : prithivMLmods/stranger-zone-collections-org-6737118adcf2cb40d66d0c7e

πŸ₯ΆPage
+ [ Stranger Zone ] : https://huggingface.co/strangerzonehf


.
.
.
@prithivMLmods πŸ€—
lewtunΒ 
posted an update 27 days ago
view post
Post
6712
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute πŸ”₯

How? By combining step-wise reward models with tree search algorithms :)

We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"

We're open sourcing the full recipe and sharing a detailed blog post.

In our blog post we cover:

πŸ“ˆ Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.

πŸŽ„ Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.

🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM

Here's the links:

- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute

- Code: https://github.com/huggingface/search-and-learn

Enjoy!
  • 2 replies
Β·
gentaiscoolΒ 
authored 5 papers 27 days ago