Downloads · 30 days
4
8% of all-time downloads
honzatoegel/Llama-2-70b-chat-hf-gramma-corrections-de-en
Llama-2-70b-chat-hf-gramma-corrections-de-en is a machine learning model from honzatoegel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
As you can see from examples bellow the output is far from ideal, and far from simple GPT/LLama2 prompt without finetuning. Quality issues: - the corrected sentences are containing some minor errors - the explanations…
Downloads · 30 days
4
8% of all-time downloads
All-time downloads
50
Public
Repo size
524 MB
Likes
0
Public
Click a slice to open those files.
.bin524 MB · 100%
From the Hugging Face model README
As you can see from examples bellow the output is far from ideal, and far from simple GPT/LLama2 prompt without finetuning. Quality issues:
'### User: Check the gramma of the following sentence and list all error and relevant corrections. Sentence:Ich mussen sehr rückwärts fahren.#### AI:Correct version of the sentence:
Ich muss sehr zurückfahren. Repairs:
'### User: Check the gramma of the following sentence and list all error and relevant corrections. Sentence:Er gehen dort, aber ich muss ander geneh.#### AI:Correct version of the sentence:
Er geht dort, aber ich muss anders gehen. Repairs:
'### User: Check the gramma of the following sentence and list all error and relevant corrections. Sentence:Habe ich das wirklich gemachen?#### AI:Correct version of the sentence:
Habe ich das wirklich gemacht? Repairs:
Trained on: 1x RTX A6000 Used: 30GB Ram, 47GB GPU, 130GB Disc 8 Epochs, cca 25 minutes, Loss: 0.36
The following bitsandbytes quantization config was used during training: