Hugging Face's logo

Spaces:
neuralmagic
/
sparse-mpt-7b-gsm8k
Running on CPU Upgrade

App Files Community
mgoin commited on
Commit
5c67b56
•
1 Parent(s): a3fa513

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -8,7 +8,7 @@ MODEL_ID = "hf:neuralmagic/mpt-7b-gsm8k-pruned60-quant"
8
 
9
  DESCRIPTION = f"""
10
  # MPT Sparse Finetuned on GSM8k with DeepSparse
11
- ![NM Logo](https://cdn-uploads.huggingface.co/production/uploads/60466e4b4f40b01b66151416/DOV5q6andhMq83TpAgaU9.jpeg)
12
  Model ID: {MODEL_ID}
13
 
14
  🚀 **Experience the power of LLM mathematical reasoning** through [our MPT sparse finetuned](https://arxiv.org/abs/2310.06927) on the [GSM8K dataset](https://huggingface.co/datasets/gsm8k).
 
8
 
9
  DESCRIPTION = f"""
10
  # MPT Sparse Finetuned on GSM8k with DeepSparse
11
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/60466e4b4f40b01b66151416/DOV5q6andhMq83TpAgaU9.jpeg" alt="NM Logo" width="200"/>
12
  Model ID: {MODEL_ID}
13
 
14
  🚀 **Experience the power of LLM mathematical reasoning** through [our MPT sparse finetuned](https://arxiv.org/abs/2310.06927) on the [GSM8K dataset](https://huggingface.co/datasets/gsm8k).