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
49
3
101
Kyle O'Brien
PRO
Kyle1668
Follow
flatstats's profile picture
geodesic-puria's profile picture
arinbjorn's profile picture
15 followers
·
6 following
https://kyleobrien.io
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a dataset
13 days ago
geodesic-research/pa-warm-start-1B-sft-mix
new
activity
13 days ago
geodesic-research/pa-warm-start-1B-sft-mix:
Migrate tool_calls/tools from JSON strings to structured columns OpenAI-convention hybrid: tool_calls is list<struct{id,type,function{name,arguments}}>, tools is list<struct{type,function{name,description,parameters}}>; arguments/parameters remain JSON-encoded strings (Arrow-clean across heterogeneous tools). JSON-string tool_calls char-iterate in Jinja chat templates, rendering one empty <tool_call><function=></function></tool_call> block per character — 4-5x length blowup and a deterministic training NaN. Renders validated byte-identical to the parsed old rows on every config.
new
activity
13 days ago
geodesic-research/pa-warm-start-1B-sft-mix:
Restore `default` config in the configs: mapping The explicit top-level `configs:` section (added by the per-config pushes) shadows the implicit default config, so load_dataset(repo, 'default') fails with "BuilderConfig 'default' not found" even though data/ holds the blended mix. This adds the data_files mapping for it (data/train-*, 265,048 rows).
View all activity
Organizations
Kyle1668
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
geodesic-research/pa-warm-start-1B-sft-mix
13 days ago
Migrate tool_calls/tools from JSON strings to structured columns OpenAI-convention hybrid: tool_calls is list<struct{id,type,function{name,arguments}}>, tools is list<struct{type,function{name,description,parameters}}>; arguments/parameters remain JSON-encoded strings (Arrow-clean across heterogeneous tools). JSON-string tool_calls char-iterate in Jinja chat templates, rendering one empty <tool_call><function=></function></tool_call> block per character — 4-5x length blowup and a deterministic training NaN. Renders validated byte-identical to the parsed old rows on every config.
1
#2 opened 13 days ago by
Kyle1668
Restore `default` config in the configs: mapping The explicit top-level `configs:` section (added by the per-config pushes) shadows the implicit default config, so load_dataset(repo, 'default') fails with "BuilderConfig 'default' not found" even though data/ holds the blended mix. This adds the data_files mapping for it (data/train-*, 265,048 rows).
#1 opened 14 days ago by
Kyle1668
New activity in
geodesic-research/nemotron-think-tokenizer
14 days ago
Add {% generation %} markers around assistant outputs Without these, apply_chat_template(return_assistant_tokens_mask=True) returns an all-zero mask, so answer_only_loss=True SFT packing silently falls back to all-token loss (now blocked by the megatron-bridge pack guard). Rendered text is byte-identical to the previous template on all conversation shapes; masks now match nemotron-think-tokenizer-prefill-parity exactly. Validated battery in GEOD-147.
#1 opened 14 days ago by
Kyle1668
New activity in
StampyAI/alignment-research-dataset
9 months ago
Dataset Viewer issue: DatasetWithScriptNotSupportedError
1
#1 opened 9 months ago by
Kyle1668
New activity in
EleutherAI/deep-ignorance-unfiltered-cb
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-strong-filter-cb
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-unfiltered-cb-lat
11 months ago
Improve model card: Add pipeline tag, library, paper, and code links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-pretraining-stage-strong-filter
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-unfiltered
11 months ago
Improve model card: Add pipeline tag, library, paper, project, and code links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-strong-filter-weak-knowledge-corrupted
11 months ago
Improve model card: Add pipeline tag, library name, and prominent links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal-cb-lat
11 months ago
Improve model card: Add pipeline tag, library name, and key resource links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-strong-filter
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
11 months ago
Improve model card: Add pipeline tag, library name, and correct links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-pretraining-stage-unfiltered
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal-cb
11 months ago
Improve model card: Add metadata, paper/project/code links, and abstract
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-weak-filter
11 months ago
Improve model card: Add pipeline tag, library name, and links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-weak-filter-pt-strong-filter-anneal
11 months ago
Improve model card: Add pipeline tag, library name, and explicit links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-strong-filter-strong-knowledge-corrupted
11 months ago
Improve model card: Add pipeline tag, library name, paper abstract, and explicit links
1
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-e2e-strong-filter-cb-lat
11 months ago
Improve model card: Add pipeline tag, library name, and paper/project/code links
#1 opened 11 months ago by
nielsr
New activity in
EleutherAI/deep-ignorance-pretraining-stage-weak-filter
11 months ago
Improve model card: Add pipeline tag, library, and explicit links
#1 opened 11 months ago by
nielsr
Load more