kerzgrr
/

Haiku-base

Text Generation

kimi-delta-attention

Model card Files Files and versions

1.32 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

kerzgrr's picture

Drop partial-epoch limitation line

c694c28 verified about 4 hours ago

tiny_gdn
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
windows_fla_patches
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
.gitattributes

1.52 kB
initial commit about 4 hours ago
README.md

7.89 kB
Drop partial-epoch limitation line about 4 hours ago
chat_template.jinja

4.21 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
config.json

1.95 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
inference.py

16.5 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
merges.txt

619 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
model.safetensors

1.31 GB
xet

Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
requirements.txt

282 Bytes
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
special_token_ids.json

217 Bytes
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
special_tokens_map.json

1.56 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
tokenizer.json

4.7 MB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
tokenizer_config.json

6.08 kB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
validation.json

505 Bytes
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago
vocab.json

1.07 MB
Upload Haiku-base (pretrain EMA @ step 8400) about 4 hours ago