RedHatAI
/

Phi-3-small-128k-instruct-quantized.w8a16

Text Generation

compressed-tensors

Model card Files Files and versions

Phi-3-small-128k-instruct-quantized.w8a16

8.63 GB

Ctrl+K

Ctrl+K

2 contributors

History: 4 commits

mgoin's picture

Updated compression_config to quantization_config

a2f09f9 verified over 1 year ago

.gitattributes

1.52 kB
initial commit over 1 year ago
README.md

7.37 kB
Create README.md over 1 year ago
cl100k_base.tiktoken

1.68 MB
Upload folder using huggingface_hub over 1 year ago
config.json

5.98 kB
Updated compression_config to quantization_config over 1 year ago
configuration_phi3_small.py

12.3 kB
Upload folder using huggingface_hub over 1 year ago
generation_config.json

143 Bytes
Upload folder using huggingface_hub over 1 year ago
model-00001-of-00002.safetensors

5 GB
xet

Upload folder using huggingface_hub over 1 year ago
model-00002-of-00002.safetensors

3.63 GB
xet

Upload folder using huggingface_hub over 1 year ago
model.safetensors.index.json

55.8 kB
Upload folder using huggingface_hub over 1 year ago
modeling_phi3_small.py

48 kB
Upload folder using huggingface_hub over 1 year ago
positional_embedding.py

11.7 kB
Upload folder using huggingface_hub over 1 year ago
recipe.yaml

174 Bytes
Upload folder using huggingface_hub over 1 year ago
special_tokens_map.json

99 Bytes
Upload folder using huggingface_hub over 1 year ago
tokenization_phi3_small.py

11.5 kB
Upload folder using huggingface_hub over 1 year ago
tokenizer_config.json

752 Bytes
Upload folder using huggingface_hub over 1 year ago
triton_blocksparse_attention_layer.py

7.2 kB
Upload folder using huggingface_hub over 1 year ago
triton_flash_blocksparse_attn.py

82.5 kB
Upload folder using huggingface_hub over 1 year ago