Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
neuralmagic
/
Phi-3-mini-128k-instruct-quantized.w8a8
like
0
Follow
Neural Magic
161
Text Generation
Transformers
Safetensors
English
phi3
conversational
custom_code
text-generation-inference
Inference Endpoints
8-bit precision
compressed-tensors
arxiv:
2210.17323
License:
mit
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
main
Phi-3-mini-128k-instruct-quantized.w8a8
2 contributors
History:
6 commits
mgoin
Updated compression_config to quantization_config
0ab444b
verified
28 days ago
.gitattributes
Safe
1.52 kB
initial commit
4 months ago
README.md
Safe
7.66 kB
Update README.md
4 months ago
added_tokens.json
Safe
293 Bytes
Upload folder using huggingface_hub
4 months ago
config.json
Safe
4.65 kB
Updated compression_config to quantization_config
28 days ago
configuration_phi3.py
Safe
11.2 kB
Upload folder using huggingface_hub
4 months ago
generation_config.json
Safe
172 Bytes
Upload folder using huggingface_hub
4 months ago
model.safetensors
Safe
4.02 GB
LFS
Upload folder using huggingface_hub
4 months ago
modeling_phi3.py
Safe
73.2 kB
Upload folder using huggingface_hub
4 months ago
recipe.yaml
Safe
381 Bytes
Upload folder using huggingface_hub
4 months ago
results_2024-07-10T00-24-05.100161.json
Safe
121 kB
Upload folder using huggingface_hub
4 months ago
special_tokens_map.json
Safe
569 Bytes
Upload folder using huggingface_hub
4 months ago
tokenizer.json
Safe
1.84 MB
Upload folder using huggingface_hub
4 months ago
tokenizer.model
Safe
500 kB
LFS
Upload folder using huggingface_hub
4 months ago
tokenizer_config.json
Safe
3.34 kB
Upload folder using huggingface_hub
4 months ago
