daekeun-ml commited on
Commit
0b62f3f
1 Parent(s): 6e563cc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -18,7 +18,7 @@ pipeline_tag: text-generation
18
  # Phi-3-medium-4k-instruct-ko-poc-v0.1
19
 
20
  ## Model Details
21
- This model is trained using unsloth toolkit based on Microsoft's phi-3 model with some Korean instruction data added to enhance its Korean generation performance
22
 
23
  Since my role is not as a working developer, but as ML Technical Specialist helping customers with quick PoCs/prototypes, and I was limited by Azure GPU resources available, I only trained with 40,000 samples on a single VM Azure Standard_NC24ads_A100_v4 for PoC purposes. Because I have not done any tokenizer extensions, you need a lot more tokens than English for text generation.
24
 
@@ -127,7 +127,7 @@ x = 4.5
127
  ```
128
 
129
  ### References
130
- - Base model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2)
131
 
132
  ## Notes
133
 
 
18
  # Phi-3-medium-4k-instruct-ko-poc-v0.1
19
 
20
  ## Model Details
21
+ This model is trained using unsloth toolkit based on Microsoft's phi-3 Phi-3-medium-4k-instruct model (https://huggingface.co/unsloth/Phi-3-medium-4k-instruct) with some Korean instruction data added to enhance its Korean generation performance
22
 
23
  Since my role is not as a working developer, but as ML Technical Specialist helping customers with quick PoCs/prototypes, and I was limited by Azure GPU resources available, I only trained with 40,000 samples on a single VM Azure Standard_NC24ads_A100_v4 for PoC purposes. Because I have not done any tokenizer extensions, you need a lot more tokens than English for text generation.
24
 
 
127
  ```
128
 
129
  ### References
130
+ - Base model: [unsloth/Phi-3-medium-4k-instruct](https://huggingface.co/unsloth/Phi-3-medium-4k-instruct)
131
 
132
  ## Notes
133