4 contributors

History: 8 commits

yangapku

fix(ckpt) fix corrupted ckpt file

712d5a5 4 days ago

.gitattributes

1.52 kB

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
LICENSE

6.96 kB

Create LICENSE 11 days ago
README.md

18.9 kB

Update README.md 8 days ago
added_tokens.json

392 Bytes

Upload folder using huggingface_hub 12 days ago
chat_template.json

1.05 kB

Upload folder using huggingface_hub 12 days ago
config.json

1.33 kB

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
generation_config.json

227 Bytes

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
merges.txt

1.67 MB

Upload folder using huggingface_hub 12 days ago
model-00001-of-00011.safetensors
3.97 GB
LFS

fix(ckpt) fix corrupted ckpt file 4 days ago
model-00002-of-00011.safetensors
3.91 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00003-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00004-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00005-of-00011.safetensors
3.91 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00006-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00007-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00008-of-00011.safetensors
3.91 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00009-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00010-of-00011.safetensors
3.99 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model-00011-of-00011.safetensors
3.33 GB
LFS

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
model.safetensors.index.json

209 kB

fix(pad zero) pad intermediate_size to 29696 to make sure quantized model can use 8 tensor-parallel in vllm 5 days ago
preprocessor_config.json

594 Bytes

Upload folder using huggingface_hub 12 days ago
special_tokens_map.json

613 Bytes

Upload folder using huggingface_hub 12 days ago
tokenizer.json

7.03 MB

Upload folder using huggingface_hub 12 days ago
tokenizer_config.json

4.3 kB

Upload folder using huggingface_hub 12 days ago
vocab.json

2.78 MB

Upload folder using huggingface_hub 12 days ago