Kkk

Michalea's activity

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

New activity in RedHatAI/GLM-5.2-speculator.dspark 6 days ago

Training trajectory

#5 opened 6 days ago by

Michalea

New activity in RedHatAI/GLM-5.2-speculator.dspark 12 days ago

Works for me

9

#3 opened about 1 month ago by

ehartford

New activity in RedHatAI/Qwen3.6-35B-A3B-speculator.dspark 13 days ago

Evals

8

#2 opened 25 days ago by

Michalea

New activity in RedHatAI/GLM-5.2-speculator.dspark 19 days ago

Comparison to MTP of GLM

🔥 2

#4 opened 19 days ago by

Michalea

New activity in Koopah/Qwen3.6-35B-A3B-NVFP4-DSPARK about 1 month ago

Nice evaluation and plots

#1 opened about 1 month ago by

Michalea

New activity in mgoin/open-perfectblend-glm5.2-regen about 2 months ago

sampling params.

1

#2 opened about 2 months ago by

Michalea

New activity in clzoro/GLM-5.1-1000000x 3 months ago

Sampling parameters

#5 opened 3 months ago by

Michalea

New activity in clzoro/GLM-5.1-OpenThoughts3-Distill 3 months ago

Sampling parameters

#3 opened 3 months ago by

Michalea

New activity in AQ-MedAI/GLM-5.1-eagle3 4 months ago

Question about train data

2

#1 opened 4 months ago by

Michalea

New activity in BLR2/Qwen3.5-9B-Eagle3-ShareGPT 6 months ago

MTP vs Eagle3

2

#1 opened 6 months ago by

Michalea

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 6 months ago

Add SWE-Bench Verified evaluation results

2

#18 opened 6 months ago by

nielsr

New activity in zai-org/GLM-5 6 months ago

The performance of dense small models is now gaining renewed attention. Could GLM's 32B/40B variants get their chance to shine?

2

#62 opened 6 months ago by

Eilian

New activity in nvidia/GLM-5-NVFP4 6 months ago

SciBench Results - methodology

#3 opened 6 months ago by

Michalea

New activity in lukealonso/GLM-5-NVFP4 6 months ago

Eval. of your quant.

#5 opened 6 months ago by

Michalea

New activity in nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 6 months ago

math-oai.yaml file for aime eval

#56 opened 6 months ago by

Michalea

New activity in festr2/GLM-5-NVFP4-MTP 6 months ago

[Bug] Eagle V2 speculative decoding crashes with NaN in logits when radix cache prefix hit occurs (SM120 / RTX PRO 6000 Blackwell)

3

#2 opened 6 months ago by

repandv

New activity in GadflyII/GLM-4.7-Flash-MTP-NVFP4 6 months ago

SGLang and MTP

1

#2 opened 6 months ago by

Michalea

New activity in Qwen/Qwen3-4B-Thinking-2507 6 months ago

RoPE theta 5mln instead of 1mln

#15 opened 6 months ago by

Michalea

New activity in lmsys/SGLang-EAGLE3-Qwen3-Next-80B-A3B-Instruct-FP8-SpecForge-Meituan 7 months ago

The comparison with the original MTP

👍 1

1

#2 opened 7 months ago by

Michalea

New activity in nvidia/Qwen3-235B-A22B-Eagle3 7 months ago

context length/number of generated tokens during training

#4 opened 7 months ago by

Michalea