Update README.md
Browse files
README.md
CHANGED
@@ -8,9 +8,10 @@ pipeline_tag: text-generation
|
|
8 |
|
9 |
Falcon-40b-chat-oasst1 is a chatbot-like model for dialogue generation. It was built by fine-tuning [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) on the [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset.
|
10 |
- The model was fine-tuned in 4-bit precision using `peft`, `transformers`, and `bitsandbytes`.
|
11 |
-
- The training relied on a method called "Low Rank Adapters" ([LoRA](https://arxiv.org/pdf/2106.09685.pdf)), specifically the [QLoRA](https://arxiv.org/abs/2305.14314) variant.
|
12 |
-
-
|
13 |
-
-
|
|
|
14 |
|
15 |
## Model Summary
|
16 |
|
@@ -163,7 +164,7 @@ print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
|
|
163 |
|
164 |
## Reproducibility
|
165 |
|
166 |
-
- See attached [Notebook](https://huggingface.co/dfurman/falcon-40b-chat-oasst1/blob/main/finetune_falcon40b_oasst1_with_bnb_peft.ipynb) for the code (and hyperparams) used to train the model.
|
167 |
|
168 |
### CUDA Info
|
169 |
|
|
|
8 |
|
9 |
Falcon-40b-chat-oasst1 is a chatbot-like model for dialogue generation. It was built by fine-tuning [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) on the [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset.
|
10 |
- The model was fine-tuned in 4-bit precision using `peft`, `transformers`, and `bitsandbytes`.
|
11 |
+
- The training relied on a method called "Low Rank Adapters" ([LoRA](https://arxiv.org/pdf/2106.09685.pdf)), specifically the [QLoRA](https://arxiv.org/abs/2305.14314) variant.
|
12 |
+
- Instead of fine-tuning the entire model you fine-tune lightweight adapters and load them inside the base model at inference.
|
13 |
+
- Training took approximately 10 hours and was executed on a workstation with a single A100-SXM NVIDIA GPU, with 37 GB of available memory.
|
14 |
+
- See attached [Colab Notebook](https://huggingface.co/dfurman/falcon-40b-chat-oasst1/blob/main/finetune_falcon40b_oasst1_with_bnb_peft.ipynb) for the code and hyperparams used to train the model.
|
15 |
|
16 |
## Model Summary
|
17 |
|
|
|
164 |
|
165 |
## Reproducibility
|
166 |
|
167 |
+
- See attached [Colab Notebook](https://huggingface.co/dfurman/falcon-40b-chat-oasst1/blob/main/finetune_falcon40b_oasst1_with_bnb_peft.ipynb) for the code (and hyperparams) used to train the model.
|
168 |
|
169 |
### CUDA Info
|
170 |
|