Hugging Face's logo

avemio
/
GRAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI

Question Answering
Safetensors
English
German
llama
German
RAG
Retrieval
Question-Answering
Summarization
Reasoning
Model card Files Community
avemio-digital commited on
Commit
ca6bb49
路
verified 路
1 Parent(s): fae756a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -106,7 +106,7 @@ The summarization task teaches models to distill complex information into clear,
106
  ### Architecture
107
 
108
 
109
- | Parameter | GRAG-MISTRAL-CPT |
110
  |-----------------------|-----------------------------------------------------------------------------------------------|
111
  | **d_model** | 4096 |
112
  | **num heads** | 32 |
@@ -124,7 +124,7 @@ The summarization task teaches models to distill complex information into clear,
124
  ### Hyperparameters
125
 
126
 
127
- | Parameter | GRAG-MISTRAL-CPT |
128
  |---------------------------|--------------------|
129
  | **warmup steps** | 50 |
130
  | **peak LR** | 5.0E-07 |
 
106
  ### Architecture
107
 
108
 
109
+ | Parameter | GRAG-PHI-CPT |
110
  |-----------------------|-----------------------------------------------------------------------------------------------|
111
  | **d_model** | 4096 |
112
  | **num heads** | 32 |
 
124
  ### Hyperparameters
125
 
126
 
127
+ | Parameter | GRAG-PHI-CPT |
128
  |---------------------------|--------------------|
129
  | **warmup steps** | 50 |
130
  | **peak LR** | 5.0E-07 |