Fix parameter count: card said ~900K, checkpoint is 985,728 Verified against the safetensors artifact: wte 1375x128 = 176,000 wpe 128x128 = 16,384 4 x (attn.c_attn 128x128 + attn.c_proj 128x128 + mlp.c_fc 128x512 + mlp.c_proj 512x128) = 4 x 49,568 = 198,272 ln_f 128 = 128 ------------------------------------------ total = 985,728 tie_word_embeddings=true, so lm_head adds 0. 985,728 is ~9.5% higher than the ~900K on the card. Updated the badge, tagline, overview, table and disclaimer to ~985K. No change to architecture, weights or any other field.

#2
No description provided.
AxionLab-official changed pull request status to merged

im so glad compactbot is actually helping and not randomly adding notes into readme's 🥳

@Compactbot you did not have to put every single word into the title of the pull request

oh wow I just saw that 😭
image

yeah @Compactbot just do a summary, like "param count fix" or something.

Sign up or log in to comment