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
CodeMasterCody3D
/
tardis-27b-ternfull
Like
0
Safetensors
qwen3_5_text
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
tardis-27b-ternfull
70.4 GB
Ctrl+K
Ctrl+K
1 contributor
History:
16 commits
CodeMasterCody3D
Upload lowrank_attnwide_rung1.json with huggingface_hub
e76c805
verified
10 days ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
18 days ago
chat_template.jinja
Safe
8.95 kB
Upload folder using huggingface_hub
18 days ago
config.json
Safe
3.29 kB
Upload folder using huggingface_hub
18 days ago
generation_config.json
Safe
214 Bytes
Upload folder using huggingface_hub
18 days ago
head_branch_fp_r16.safetensors
16.2 MB
xet
head Doctor rank 16 on the FP-body-trained ternary head: KL 0.0470->0.0451, probe 1.0740x -> 1.0712x
13 days ago
head_branch_fp_r256.safetensors
260 MB
xet
head Doctor rank 256 on the FP-body-trained ternary head: KL 0.0470->0.0428, probe 1.0740x -> 1.0683x
13 days ago
head_branch_fp_r512.safetensors
519 MB
xet
head Doctor rank 512 on the FP-body-trained ternary head: KL 0.0470->0.0412, probe 1.0740x -> 1.0669x
13 days ago
head_branch_fp_r64.safetensors
64.9 MB
xet
head Doctor rank 64 on the FP-body-trained ternary head: KL 0.0470->0.0429, probe 1.0740x -> 1.0691x
13 days ago
head_rank_ladder.json
Safe
1.39 kB
head Doctor rank ladder: held-out KL + probe vs branch size
13 days ago
kv_branches_rank16.pt
12.6 MB
xet
trained k1-KV compensation branches (rank 16, k/v_proj, post-RoPE rotation): held-out gap +0.1711 -> -0.0179
14 days ago
kv_branches_rank16_v2.pt
12.6 MB
xet
re-fit k1-KV branches (v2, trained with live Doctors)
14 days ago
lowrank.safetensors
920 MB
xet
Upload folder using huggingface_hub
18 days ago
lowrank_attnwide_rung1.json
1.38 kB
Upload lowrank_attnwide_rung1.json with huggingface_hub
10 days ago
lowrank_attnwide_rung1.safetensors
2.43 GB
xet
Upload lowrank_attnwide_rung1.safetensors with huggingface_hub
10 days ago
lowrank_kv_merged.safetensors
927 MB
xet
MERGED Doctors + re-fit k1-KV rank-16 (LIVE-Doctors training; held-out gap +0.0874 -> -0.0043, 105% closed)
14 days ago
lowrank_wide256.safetensors
1.21 GB
xet
widened attention branches: 16 attn layers q/k/v/o r8/r64 -> r256 (identity at step 0, new A columns zero)
10 days ago
model-00001-of-00002.safetensors
49.8 GB
xet
Upload folder using huggingface_hub
18 days ago
model-00002-of-00002.safetensors
3.97 GB
xet
Upload folder using huggingface_hub
18 days ago
model.safetensors.index.json
Safe
83.9 kB
Upload folder using huggingface_hub
18 days ago
shadow_head_fp.safetensors
5.09 GB
xet
shadow head trained on the FULL FP body (head gaining everything): KL 0.1844->0.0788, head probe 1.1028x, 1500 steps
14 days ago
shadow_head_fp_v2.safetensors
5.09 GB
xet
shadow head on the FULL FP body v2 (lloyd 3, cosine, batch 4->8, polyak 200, init shadow_head.safetensors): held-out KL 0.0788->0.0470, wikitext probe 1.0740x, 1500 steps
14 days ago
tokenizer.json
Safe
20 MB
xet
Upload folder using huggingface_hub
18 days ago
tokenizer_config.json
Safe
1.12 kB
Upload folder using huggingface_hub
18 days ago