Chmielewski

Eryk-Chmielewski's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 4 months ago

The Universal Weight Subspace Hypothesis

Paper • 2512.05117 • Published Dec 4, 2025 • 3 •

3

New activity in QuantTrio/Qwen3.6-35B-A3B-AWQ 6 months ago

It doesn't terminate the reasoning section properly.

1

#5 opened 7 months ago by

Eryk-Chmielewski

commented a paper 8 months ago

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

Paper • 2603.04918 • Published Mar 5 • 56 •

7

commented 3 papers about 1 year ago

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Paper • 2508.15884 • Published Aug 21, 2025 • 5 •

5

Scaling Agents via Continual Pre-training

Paper • 2509.13310 • Published Sep 16, 2025 • 118 •

9

Lost in Transmission: When and Why LLMs Fail to Reason Globally

Paper • 2505.08140 • Published May 13, 2025 • 1 •

1

New activity in Qwen/Qwen3-4B-Instruct-2507-FP8 about 1 year ago

Broken inference on vllm

#2 opened about 1 year ago by

Eryk-Chmielewski

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF about 1 year ago

qwen3moe instead of qwen3_moe?

3

#5 opened about 1 year ago by

bnjmnmarie

commented 7 papers about 1 year ago

Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling

Paper • 2509.00605 • Published Aug 30, 2025 • 43 •

5

Fast and Simplex: 2-Simplicial Attention in Triton

Paper • 2507.02754 • Published Jul 3, 2025 • 25 •

3

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning

Paper • 2507.10624 • Published Jul 14, 2025 • 2 •

1

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

Paper • 2509.03312 • Published Sep 3, 2025 • 6 •

2

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Paper • 2508.15884 • Published Aug 21, 2025 • 5 •

5

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Paper • 2508.15884 • Published Aug 21, 2025 • 5 •

5

MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark

Paper • 2508.07575 • Published Aug 11, 2025 • 1 •

2

New activity in unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit over 1 year ago

Doesn't work with vLLM

5

#2 opened over 1 year ago by

Eryk-Chmielewski

New activity in ModelCloud/DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v1 almost 2 years ago

Answers without <think> tag

5

#2 opened almost 2 years ago by

Eryk-Chmielewski

New activity in ruliad/deepthought-8b-llama-v0.01-alpha almost 2 years ago

Add Deepthought chat template

1

#2 opened almost 2 years ago by

alpindale

New activity in facebook/MobileLLM-125M about 2 years ago

Unable to run with default instructions on Colab

👀 1

6

#3 opened about 2 years ago by

rahulmanuwas