15.7 GB

1 contributor

History: 31 commits

AP314159

Fix: Add complete model architecture to mla.py

b700517 verified 5 months ago

.gitattributes
1.57 kB

Adding tokenizer files 5 months ago
README.md
5.17 kB

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
added_tokens.json
605 Bytes

Adding tokenizer files 5 months ago
chat_template.jinja
2.51 kB

Adding tokenizer files 5 months ago
config.json
1.16 kB

Fix: Align model_type to 'llamamla' 5 months ago
configuration_llamamla.py
847 Bytes

Fix: Update config class to inherit from LlamaConfig 5 months ago
generation_config.json
243 Bytes

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
merges.txt
1.67 MB

Adding tokenizer files 5 months ago
mla.py
20.8 kB

Fix: Add complete model architecture to mla.py 5 months ago
model-00001-of-00004.safetensors
5 GB
xet

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
model-00002-of-00004.safetensors
5 GB
xet

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
model-00003-of-00004.safetensors
4.62 GB
xet

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
model-00004-of-00004.safetensors
1.09 GB
xet

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
model.safetensors.index.json
26.3 kB

Initial upload of Qwen2.5-7B-Instruct-deepseek with custom MLA architecture 5 months ago
modeling_llamamla.py
1.54 kB

Update modeling_llamamla.py 5 months ago
special_tokens_map.json
613 Bytes

Adding tokenizer files 5 months ago
tokenizer.json
11.4 MB
xet

Adding tokenizer files 5 months ago
tokenizer_config.json
4.88 kB

Adding tokenizer files 5 months ago
vocab.json
2.78 MB

Adding tokenizer files 5 months ago