v1.0

openai/clip-vit-large-patch14-336/tokenizer_config.json

+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch32", "model_max_length": 77, "special_tokens_map_file": "/home/suraj/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "tokenizer_class": "CLIPTokenizer"}
\ No newline at end of file

pretrain.sh

+bash run.sh mobilevlm_v2_1.7b pretrain mtgv/MobileVLM_V2-1.7B openai/clip-vit-large-patch14-336

requirements.txt

+#torch==2.0.1
+#torchvision==0.15.2
+#deepspeed==0.9.5
+transformers==4.33.1
+tokenizers==0.13.3
+sentencepiece==0.1.99
+shortuuid==1.0.11
+accelerate==0.21.0
+peft==0.4.0
+#bitsandbytes==0.41.0
+pydantic==1.10.13
+markdown2==2.4.8
+numpy
+scikit-learn==1.2.2
+gradio==3.35.2
+requests==2.28.2
+httpx==0.24.0
+uvicorn==0.22.0
+fastapi==0.103.0
+einops==0.6.1
+einops-exts==0.0.4
+timm==0.9.12
+#flash-attn==2.3.2