Fix padding token

#1
by jbochi - opened
Files changed (4) hide show
  1. .gitattributes +0 -1
  2. README.md +2 -6
  3. model-q4k.gguf +0 -3
  4. model-q6k.gguf +0 -3
.gitattributes CHANGED
@@ -34,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
- *.gguf filter=lfs diff=lfs merge=lfs -text
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
README.md CHANGED
@@ -484,15 +484,11 @@ Find below some example scripts on how to use the model:
484
  <details>
485
  <summary> Click to expand </summary>
486
 
487
- First, install the Python packages that are required:
488
-
489
- `pip install transformers accelerate sentencepiece`
490
-
491
  ```python
492
- from transformers import T5ForConditionalGeneration, T5Tokenizer
493
 
494
  model_name = 'jbochi/madlad400-7b-mt'
495
- model = T5ForConditionalGeneration.from_pretrained(model_name, device_map="auto")
496
  tokenizer = T5Tokenizer.from_pretrained(model_name)
497
 
498
  text = "<2pt> I love pizza!"
 
484
  <details>
485
  <summary> Click to expand </summary>
486
 
 
 
 
 
487
  ```python
488
+ from transformers import T5ForConditionalGeneration, T5Tokenizer, GenerationConfig
489
 
490
  model_name = 'jbochi/madlad400-7b-mt'
491
+ model = T5ForConditionalGeneration.from_pretrained(model_name, device="auto")
492
  tokenizer = T5Tokenizer.from_pretrained(model_name)
493
 
494
  text = "<2pt> I love pizza!"
model-q4k.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcf42f3f2db84d171585de558c17b725a166fcae7b76a4c9ba0edd47c88bdf96
3
- size 4668768576
 
 
 
 
model-q6k.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f56153becae886067316a5fa529127fce0b6db16e662a904b5709388f9b62545
3
- size 6807667008