commit 7361467f0566aed6d94560827234616a7b17d374 Author: ModelHub XC Date: Sun Jun 7 07:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mrm8488/bloom-560m-finetuned-sd-prompts Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4867779 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..0348ea9 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +checkpoint-*/ \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6bb969 --- /dev/null +++ b/README.md @@ -0,0 +1,114 @@ +--- +license: bigscience-bloom-rail-1.0 +tags: +- generated_from_trainer +- stable-diffusion +- diffusion +model-index: +- name: bloom-560m-finetuned-sd-prompts + results: [] + +datasets: + - Gustavosta/Stable-Diffusion-Prompts + +widget: +- text: "Prompt: young, curly haired, redhead Natalie Portman as a" +- text: "Prompt: a powerful energy woman, by alexander fedosav" + +inference: + parameters: + eos_token_id: 2 + max_length: 128 + + +--- + + + +# bloom-560m-finetuned-sd-prompts + +This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the [Gustavosta/Stable-Diffusion-Prompts](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts) dataset. +It achieves the following results on the evaluation set: +- Loss: 0.8742 + + +## Example of usage + +```py +import torch +from transformers import BloomTokenizerFast, BloomForCausalLM + +device = 'cuda' if torch.cuda.is_available() else 'cpu' +ckpt = 'mrm8488/bloom-560m-finetuned-sd-prompts' + +tokenizer = BloomTokenizerFast.from_pretrained(ckpt) +model = BloomForCausalLM.from_pretrained(ckpt).to(device) + +def generate_prompt(text): + inputs = tokenizer(text, return_tensors='pt') + input_ids = inputs.input_ids.to(device) + attention_mask = inputs.attention_mask.to(device) + output = model.generate(input_ids, attention_mask=attention_mask, repetition_penalty=1.05, max_length=2048, eos_token_id=tokenizer.eos_token_id) + + return tokenizer.decode(output[0], skip_special_tokens=False) + +text = "Prompt: pikachu dinning in the eiffel tower" + +generate_prompt(text) + +# Output: Prompt: pikachu dinning in the eiffel tower, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha +``` + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-05 +- train_batch_size: 1 +- eval_batch_size: 1 +- seed: 42 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 4 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: linear +- num_epochs: 2 +- mixed_precision_training: Native AMP + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:-----:|:----:|:---------------:| +| 2.6743 | 0.17 | 100 | 2.0891 | +| 1.8919 | 0.33 | 200 | 1.7191 | +| 1.5907 | 0.5 | 300 | 1.4454 | +| 1.3865 | 0.67 | 400 | 1.3247 | +| 1.2487 | 0.83 | 500 | 1.2150 | +| 1.1565 | 1.0 | 600 | 1.1031 | +| 0.896 | 1.17 | 700 | 1.0612 | +| 0.8389 | 1.33 | 800 | 0.9994 | +| 0.8071 | 1.5 | 900 | 0.9530 | +| 0.7628 | 1.67 | 1000 | 0.9206 | +| 0.7423 | 1.83 | 1100 | 0.8883 | +| 0.7155 | 2.0 | 1200 | 0.8742 | + + +### Framework versions + +- Transformers 4.22.1 +- Pytorch 1.12.1+cu113 +- Datasets 2.5.1 +- Tokenizers 0.12.1 diff --git a/config.json b/config.json new file mode 100644 index 0000000..97ef117 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "_name_or_path": "bigscience/bloom-560m", + "apply_residual_connection_post_layernorm": false, + "architectures": [ + "BloomForCausalLM" + ], + "attention_dropout": 0.0, + "attention_softmax_in_fp32": true, + "bias_dropout_fusion": true, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_dropout": 0.0, + "hidden_size": 1024, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "masked_softmax_fusion": true, + "model_type": "bloom", + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "offset_alibi": 100, + "pad_token_id": 3, + "pretraining_tp": 1, + "seq_length": 2048, + "skip_bias_add": true, + "skip_bias_add_qkv": false, + "slow_but_exact": false, + "torch_dtype": "float32", + "transformers_version": "4.22.1", + "unk_token_id": 0, + "use_cache": false, + "vocab_size": 250880 +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..01f8204 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eecaa7c1b1149a41589acab54d207ee940fe3c7fd3299537cf1a8fe86cedad3d +size 2236892306 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..b3a9e76 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fcbdaa06eebfb1ee28adbabb6d641bef7b455fa25dbb1e1ae945964cae115a2 +size 2236955191 diff --git a/runs/Sep27_11-50-57_163646036bff/1664279476.271967/events.out.tfevents.1664279476.163646036bff.68.1 b/runs/Sep27_11-50-57_163646036bff/1664279476.271967/events.out.tfevents.1664279476.163646036bff.68.1 new file mode 100644 index 0000000..0837a40 --- /dev/null +++ b/runs/Sep27_11-50-57_163646036bff/1664279476.271967/events.out.tfevents.1664279476.163646036bff.68.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554331629e38a2c37d75d002710d137c6966f0cd7adc37f5f047dc99970bb5d7 +size 5548 diff --git a/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664279476.163646036bff.68.0 b/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664279476.163646036bff.68.0 new file mode 100644 index 0000000..72b3330 --- /dev/null +++ b/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664279476.163646036bff.68.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:483ed123d94beae4d9f1b1fa9f7b4f9481da7bb2d84e0d795affb61c766f5d37 +size 9356 diff --git a/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664282954.163646036bff.68.2 b/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664282954.163646036bff.68.2 new file mode 100644 index 0000000..4e8043d --- /dev/null +++ b/runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664282954.163646036bff.68.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01527bef8475c929d58d5df85f0b862636b7a737e89c715330a95bc5b5f4bb4a +size 311 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..fdafe48 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a4fa803 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5 +size 14500443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3ce2a29 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,12 @@ +{ + "add_prefix_space": false, + "bos_token": "", + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "name_or_path": "bigscience/bloom-560m", + "pad_token": "", + "padding_side": "left", + "special_tokens_map_file": null, + "tokenizer_class": "BloomTokenizer", + "unk_token": "" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..582d8eb --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ec16c1d2f7cd3fbadcb6fd0f7701b4449c87e76e12b26e1b50a29ab9847d61 +size 3375