Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Aether
aethertp
3
6
Follow
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
aethertp/PicoLM-V2.1-81M-Instruct
new
activity
7 days ago
aethertp/PicoLM-V2.1-81M-Instruct:
Drop redundant untied lm_head.weight (Option 1) The checkpoint stored both tok_embeddings.weight and a separate lm_head.weight, each [24576, 576] = 14,155,776 params, even though config.json sets tie_word_embeddings: true. At runtime the head is tied to the embedding, so lm_head.weight is never read. This removes that one tensor. Verified: - 201 -> 200 tensors; stored elements 96,017,472 -> 81,861,696 (exactly the card's count) - file 192,054,704 -> 163,743,061 bytes (-28.3 MB) - loaded both versions with the repo's own PicoLMV2ForCausalLM: identical logits on fixed inputs (max |diff| = 0.0), same 81,861,696 unique params, head tied to embedding in both. Requested by aethertp in the discussion (Option 1).
new
activity
8 days ago
aethertp/PicoLM-V2.1-81M-Instruct:
Checkpoint stores an untied lm_head: 96.0M params on disk vs 81.86M on the card
View all activity
Organizations
None yet
aethertp
's datasets
None public yet
