EssentialAI/rnj-1-instruct
8B
•
Updated
•
3.15k
•
73
Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
liked
a model
about 5 hours ago
EssentialAI/rnj-1-instruct
liked
a model
4 days ago
Skywork/R1V4
new activity
9 days ago
ChenkinNoob/ChenkinNoob-XL-V0.1:Diffusers library format?
Organizations
liked
a
model
about 5 hours ago
liked
a
model
4 days ago
Diffusers library format?
#4 opened 9 days ago
by
djuna
liked
a
Space
9 days ago
liked
a
model
9 days ago
reacted to
grimjim's
post with 🤗
12 days ago
Post
2829
I wanted to call attention to Arli Ai's success in applying my recent modifications to refusal ablation to a MoE model successfully. Nice work,
@OwenArli
!
ArliAI/GLM-4.5-Air-Derestricted
Ablation on a MoE model is no small thing; I expect preserving norms/magnitudes during intervention better respects routing compared to naive refusal ablation.
(I would have tagged their org earlier, but that feature seemed to be broken via "@")
ArliAI
ArliAI/GLM-4.5-Air-Derestricted
Ablation on a MoE model is no small thing; I expect preserving norms/magnitudes during intervention better respects routing compared to naive refusal ablation.
(I would have tagged their org earlier, but that feature seemed to be broken via "@")
ArliAI
- 4 replies
upvoted
an
article
17 days ago
Article
DeLERP: Decomposed Linear Interpolation for Model Merging
•
7
reacted to
grimjim's
post with 🔥
18 days ago
Post
5011
Implemented a proof of concept sampler in pure PyTorch and transformers.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
Max P consists of a dynamic token filter which applies Winsorization to cap the probabilties of top tokens. Specifically, a base probability in the range of [0,1] is used to cap individual token probability; the sampler then redistributes excess proportionally.
https://github.com/jim-plus/maxp-sampler-poc
Combined with Temperature and Min P, this could represent a more intuitive way of reducing repetition in text generation.
-
- 2 replies
upvoted
a
paper
22 days ago
liked
a
model
24 days ago
reacted to
Locutusque's
post with 🔥
26 days ago
Post
2640
🚀 AutoXLA - Accelerating Large Models on TPU
AutoXLA is an experimental library that automates the distribution, optimization, and quantization of large language models for TPUs using PyTorch/XLA. It extends the Hugging Face Transformers interface with TPU-aware features such as automatic sharding, custom attention kernels, and quantization-aware loading, making large-scale deployment and training both simpler and faster.
With quantization and Splash Attention kernels, AutoXLA achieves up to 4× speedups over standard Flash Attention implementations, significantly improving throughput for both inference and training workloads.
Whether you’re experimenting with distributed setups (FSDP, 2D, or 3D sharding) or optimizing memory via LanguageModelQuantizer, AutoXLA is built to make scaling LLMs on TPU seamless.
⚠️ Note: This is an experimental repository. Expect rough edges! Please report bugs or unexpected behavior through GitHub issues.
🔗 GitHub Repository: https://github.com/Locutusque/AutoXLA
AutoXLA is an experimental library that automates the distribution, optimization, and quantization of large language models for TPUs using PyTorch/XLA. It extends the Hugging Face Transformers interface with TPU-aware features such as automatic sharding, custom attention kernels, and quantization-aware loading, making large-scale deployment and training both simpler and faster.
With quantization and Splash Attention kernels, AutoXLA achieves up to 4× speedups over standard Flash Attention implementations, significantly improving throughput for both inference and training workloads.
Whether you’re experimenting with distributed setups (FSDP, 2D, or 3D sharding) or optimizing memory via LanguageModelQuantizer, AutoXLA is built to make scaling LLMs on TPU seamless.
⚠️ Note: This is an experimental repository. Expect rough edges! Please report bugs or unexpected behavior through GitHub issues.
🔗 GitHub Repository: https://github.com/Locutusque/AutoXLA
reacted to
onekq's
post with 🧠
26 days ago
Post
2438
Instead of architectural upgade, each major model drop nowadays perfects a regional innovation. What Kimi brought to spot light this time is quantization aware training (QAT). I wrote an article to explain it and why it matters to reasoning models.
https://huggingface.co/blog/onekq/qat-bonsai
If you are interested in this kind of posts, I will introduce the Muon optimizers, another technology behind Kimi success.
https://huggingface.co/blog/onekq/qat-bonsai
If you are interested in this kind of posts, I will introduce the Muon optimizers, another technology behind Kimi success.
liked
a
model
26 days ago
liked
2
models
about 1 month ago
reacted to
onekq's
post with 👍
about 1 month ago
Post
3663
Context rot is such a catchy phrase, but the problem has been identified 2+ years ago, called attention decay.
Lost in the Middle: How Language Models Use Long Contexts (2307.03172)
I spotted the same problem in coding tasks, and documented in my book (https://www.amazon.com/dp/9999331130).
Why did this problem become hot again? This is because many of us thought the problem has been solved by long context models, which is not true.
Here we were misled by benchmarks. Most long-context benchmarks build around the QA scenario, i.e. "finding needle in haystack". But in agentic scenarios, the model needs to find EVERYTHING in the haystack, and just can't afford enough attention for this challenge.
Lost in the Middle: How Language Models Use Long Contexts (2307.03172)
I spotted the same problem in coding tasks, and documented in my book (https://www.amazon.com/dp/9999331130).
Why did this problem become hot again? This is because many of us thought the problem has been solved by long context models, which is not true.
Here we were misled by benchmarks. Most long-context benchmarks build around the QA scenario, i.e. "finding needle in haystack". But in agentic scenarios, the model needs to find EVERYTHING in the haystack, and just can't afford enough attention for this challenge.
- 6 replies
No lightning attention?
3
#8 opened about 1 month ago
by
djuna
liked
a
model
about 1 month ago
upvoted
an
article
about 1 month ago
Article
Projected Abliteration
•
30