Update README.md

README.md

@@ -32,7 +32,6 @@ import torch
 from PIL import Image
 from transformers import AutoModelForVision2Seq, AutoProcessor, AutoTokenizer, TextStreamer
 
-
 model_id = "hiyouga/PaliGemma-3B-Chat-v0.1"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 processor = AutoProcessor.from_pretrained(model_id)
@@ -46,7 +45,7 @@ pixel_values = processor(images=[image], return_tensors="pt").to(model.device)["
 messages = [
     {"role": "user", "content": "What is in this image?"}
 ]
-input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
 image_token_id = tokenizer.convert_tokens_to_ids("<image>")
 image_prefix = torch.empty((1, getattr(processor, "image_seq_length")), dtype=input_ids.dtype).fill_(image_token_id)
 input_ids = torch.cat((image_prefix, input_ids), dim=-1).to(model.device)
@@ -70,6 +69,48 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine
 - mixed_precision_training: bf16
 
+<details>
+<summary><b>Show Llama Factory Config [CLICK TO EXPAND]</b></summary>
+
+```yaml
+### model
+model_name_or_path: google/paligemma-3b-mix-448
+visual_inputs: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+
+### ddp
+ddp_timeout: 180000000
+deepspeed: examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: identity,llava_1k_en,llava_1k_zh
+template: gemma
+cutoff_len: 1536
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/paligemma-chat
+logging_steps: 10
+save_steps: 100
+plot_loss: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 0.00001
+num_train_epochs: 3.0
+lr_scheduler_type: cosine
+warmup_steps: 50
+bf16: true
+```
+
+</details>
+
 ### Framework versions
 
 - Pytorch 2.3.0