Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
In a Training Loop 🔄
215.7
TFLOPS
79
135
307
Asankhaya Sharma
codelion
Follow
madoss's profile picture
annekethvij's profile picture
PlatonicSkeptic's profile picture
412 followers
·
19 following
http://asankhaya.github.io/
asankhaya
codelion
asankhaya
AI & ML interests
Creator of OptiLLM, OpenEvolve, Adaptive Classifier, and Ellora. Pioneering a new category in AI infrastructure: inference-time compute for LLMs.
Recent Activity
new
activity
about 1 hour ago
mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit:
Tool Calling Failure: Qwen3.6-35B-A3B-OptiQ-4bit on oMLX
reacted
to
their
post
with 👀
about 2 hours ago
Inspired by the Nemotron Diffusion recipe, check out dhara-250m: a 250M experimental language model that supports three decoding modes from one set of weights: autoregressive, block-diffusion, and self-speculation. It is small, easy to try, and meant for exploring diffusion-style decoding and latency tradeoffs in compact LMs. Model: https://huggingface.co/codelion/dhara-250m Try the chat demo here: https://huggingface.co/spaces/codelion/dhara-chat
reacted
to
their
post
with 🤗
about 2 hours ago
Inspired by the Nemotron Diffusion recipe, check out dhara-250m: a 250M experimental language model that supports three decoding modes from one set of weights: autoregressive, block-diffusion, and self-speculation. It is small, easy to try, and meant for exploring diffusion-style decoding and latency tradeoffs in compact LMs. Model: https://huggingface.co/codelion/dhara-250m Try the chat demo here: https://huggingface.co/spaces/codelion/dhara-chat
View all activity
Organizations
codelion
's datasets
46
Sort: Recently updated
codelion/logical-puzzles-cot
Viewer
•
Updated
about 3 hours ago
•
2.29k
•
131
•
1
codelion/sutra-improved-100M
Viewer
•
Updated
Mar 29
•
414k
•
167
•
2
codelion/sutra-magpie-sft
Viewer
•
Updated
Mar 8
•
20.7k
•
33
•
2
codelion/sutra-30k-seeds
Viewer
•
Updated
Mar 8
•
30.3k
•
53
•
2
codelion/sutra-10M
Viewer
•
Updated
Mar 8
•
7.25k
•
45
•
3
codelion/sutra-100M
Viewer
•
Updated
Mar 8
•
70.4k
•
88
•
2
codelion/sutra-1B
Viewer
•
Updated
Mar 8
•
429k
•
3.32k
•
2
codelion/sutra-10B
Viewer
•
Updated
Mar 8
•
5M
•
466
•
8
codelion/synth-1B
Viewer
•
Updated
Nov 11, 2025
•
822k
•
51
•
1
codelion/synth-100M
Viewer
•
Updated
Nov 11, 2025
•
100k
•
16
codelion/synth-10M
Viewer
•
Updated
Nov 11, 2025
•
13.3k
•
23
codelion/finewiki-1B
Viewer
•
Updated
Nov 2, 2025
•
52.7k
•
42
•
2
codelion/finewiki-10M
Viewer
•
Updated
Nov 2, 2025
•
4.91k
•
124
•
2
codelion/finewiki-100M
Viewer
•
Updated
Nov 2, 2025
•
68k
•
39
•
2
codelion/fineweb-edu-1B
Viewer
•
Updated
Nov 2, 2025
•
970k
•
1.41k
•
10
codelion/fineweb-edu-100M
Viewer
•
Updated
Nov 2, 2025
•
115k
•
117
•
3
codelion/fineweb-edu-10M
Viewer
•
Updated
Nov 2, 2025
•
9.46k
•
226
•
3
codelion/dclm-baseline-1B
Viewer
•
Updated
Nov 2, 2025
•
774k
•
972
•
6
codelion/dclm-baseline-100M
Viewer
•
Updated
Nov 2, 2025
•
77.2k
•
48
•
2
codelion/dclm-baseline-10M
Viewer
•
Updated
Nov 2, 2025
•
7.95k
•
53
•
2
codelion/finepdfs-1B
Viewer
•
Updated
Nov 2, 2025
•
186k
•
907
•
4
codelion/finepdfs-100M
Viewer
•
Updated
Nov 2, 2025
•
18.6k
•
38
•
2
codelion/finepdfs-10M
Viewer
•
Updated
Nov 2, 2025
•
7.54k
•
80
•
2
codelion/execution-world-model-dataset
Viewer
•
Updated
Oct 14, 2025
•
621
•
13
codelion/SimpleQA-Verified
Viewer
•
Updated
Sep 11, 2025
•
1k
•
425
•
1
codelion/ifeval-high-quality-dpo
Viewer
•
Updated
Sep 9, 2025
•
501
•
54
codelion/Qwen2.5-Coder-0.5B-Instruct-security-preference
Viewer
•
Updated
Aug 2, 2025
•
245
•
11
codelion/Qwen2.5-Coder-0.5B-Instruct-progressive-2M-context
Viewer
•
Updated
Jul 20, 2025
•
400
•
9
codelion/Llama-3.2-1B-Instruct-magpie-tool-calling
Viewer
•
Updated
Jul 18, 2025
•
1.2k
•
247
•
1
codelion/Qwen3-0.6B-icm-dpo-pairs
Viewer
•
Updated
Jul 18, 2025
•
122
•
11
Previous
1
2
Next