tturing
/

DM-KDAGQA-1.7B-MP

kimi-delta-attention

Model card Files Files and versions

DM-KDAGQA-1.7B-MP

3.33 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

tturing's picture

Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code)

51b77b4 verified about 2 months ago

.gitattributes
1.52 kB
initial commit about 2 months ago
README.md
5.05 kB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
config.json
1.69 kB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
config.train.json
1.53 kB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
configuration_bqalm.py
11.9 kB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
model.safetensors
3.33 GB
xet

Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
modeling_bqalm.py
31.4 kB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
tokenizer.json
3.62 MB
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago
tokenizer_config.json
421 Bytes
Add Q35KDA_clean_sdpa_ffn8_hd128_11785_fm128: KDA:GQA 1.7B, MP (clean) arm, seed 11785 (standalone, trust_remote_code) about 2 months ago