PrunaAI
/

microsoft-Phi-3-small-128k-instruct-bnb-8bit-smashed

8-bit precision

Model card Files Files and versions

microsoft-Phi-3-small-128k-instruct-bnb-8bit-smashed

7.81 GB

1 contributor

History: 4 commits

sharpenb's picture

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51

16a59ec verified about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

5.41 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
cl100k_base.tiktoken

1.68 MB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
config.json

5.71 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
configuration_phi3_small.py

12.3 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
generation_config.json

143 Bytes

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
model-00001-of-00002.safetensors

5 GB
xet

804a18d4ba628a09f8b6fc64f279f00f46db70feb08b48eaf6d2e0d47eaef3c5 about 1 year ago
model-00002-of-00002.safetensors

2.81 GB
xet

b7698273658dab80594d7ba974ceee4d13c5b61ca8a62b13a7fb5c35501d92f8 about 1 year ago
model.safetensors.index.json

42.3 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
modeling_phi3_small.py

48 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
positional_embedding.py

11.7 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
smash_config.json

1.04 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
special_tokens_map.json

99 Bytes

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
tokenization_phi3_small.py

11.5 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
tokenizer_config.json

771 Bytes

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
triton_blocksparse_attention_layer.py

7.2 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago
triton_flash_blocksparse_attn.py

82.5 kB

70cd13ae8836ed7a79b3a852e33064b17d1df92f602beadf10ee7f905809fb51 about 1 year ago