commit 1dfab32411fe0285516094e5a44c36f2554d4bb3 Author: ModelHub XC Date: Tue Sep 8 20:06:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: adept/fuyu-8b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d6bd709 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +*.ckpt 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f840a26 --- /dev/null +++ b/README.md @@ -0,0 +1,129 @@ +--- +license: cc-by-nc-4.0 +--- +# Fuyu-8B Model Card + +We’re releasing Fuyu-8B, a small version of the multimodal model that powers our product. The model is available on HuggingFace. We think Fuyu-8B is exciting because: +1. It has a much simpler architecture and training procedure than other multi-modal models, which makes it easier to understand, scale, and deploy. +2. It’s designed from the ground up for digital agents, so it can support arbitrary image resolutions, answer questions about graphs and diagrams, answer UI-based questions, and do fine-grained localization on screen images. +3. It’s fast - we can get responses for large images in less than 100 milliseconds. +4. Despite being optimized for our use-case, it performs well at standard image understanding benchmarks such as visual question-answering and natural-image-captioning. + +Please note that **the model we have released is a base model. We expect you to need to finetune the model for specific use cases like verbose captioning or multimodal chat.** In our experience, the model responds well to few-shotting and fine-tuning for a variety of use-cases. + +## Model + +[Fuyu-8B](https://www.adept.ai/blog/fuyu-8b) is a multi-modal text and image transformer trained by [Adept AI](https://www.adept.ai/). + +Architecturally, Fuyu is a vanilla decoder-only transformer - there is no image encoder. +Image patches are instead linearly projected into the first layer of the transformer, bypassing the embedding lookup. +We simply treat the transformer decoder like an image transformer (albeit with no pooling and causal attention). +See the below diagram for more details. + +![architecture](architecture.png) + +This simplification allows us to support arbitrary image resolutions. +To accomplish this, we treat the sequence of image tokens like the sequence of text tokens. +We remove image-specific position embeddings and feed in as many image tokens as necessary in raster-scan order. +To tell the model when a line has broken, we simply use a special image-newline character. +The model can use its existing position embeddings to reason about different image sizes, and we can use images of arbitrary size at training time, removing the need for separate high and low-resolution training stages. + +### Model Description + +- **Developed by:** Adept-AI +- **Model type:** Decoder-only multi-modal transformer model +- **License:** [CC-BY-NC](https://creativecommons.org/licenses/by-nc/4.0/deed.en) +- **Model Description:** This is a multi-modal model that can consume images and text and produce text. +- **Resources for more information:** Check out our [blog post](https://www.adept.ai/blog/fuyu-8b). + +## Evaluation +Though not the focus of this model, we did evaluate it on standard image understanding benchmarks: + +| Eval Task | Fuyu-8B | Fuyu-Medium | LLaVA 1.5 (13.5B) | QWEN-VL (10B) | PALI-X (55B) | PALM-e-12B | PALM-e-562B | +| ------------------- | ------- | ----------------- | ----------------- | ------------- | ------------ | ---------- | ----------- | +| VQAv2 | 74.2 | 77.4 | 80 | 79.5 | 86.1 | 76.2 | 80.0 | +| OKVQA | 60.6 | 63.1 | n/a | 58.6 | 66.1 | 55.5 | 66.1 | +| COCO Captions | 141 | 138 | n/a | n/a | 149 | 135 | 138 | +| AI2D | 64.5 | 73.7 | n/a | 62.3 | 81.2 | n/a | n/a | + +## How to Use + +You can load the model and perform inference as follows: +```python +from transformers import FuyuProcessor, FuyuForCausalLM +from PIL import Image +import requests + +# load model and processor +model_id = "adept/fuyu-8b" +processor = FuyuProcessor.from_pretrained(model_id) +model = FuyuForCausalLM.from_pretrained(model_id, device_map="cuda:0") + +# prepare inputs for the model +text_prompt = "Generate a coco-style caption.\n" +url = "https://huggingface.co/adept/fuyu-8b/resolve/main/bus.png" +image = Image.open(requests.get(url, stream=True).raw) + +inputs = processor(text=text_prompt, images=image, return_tensors="pt").to("cuda:0") + +# autoregressively generate text +generation_output = model.generate(**inputs, max_new_tokens=7) +generation_text = processor.batch_decode(generation_output[:, -7:], skip_special_tokens=True) +assert generation_text == ['A blue bus parked on the side of a road.'] +``` + +N.B.: The token `|SPEAKER|` is a placeholder token for image patch embeddings, so it will show up in the model context (e.g., in the portion of `generation_output` representing the model context). +`|NEWLINE|` is the "image newline" token, denoting new rows in the raster scan order input of the image patches. +`\x04` is the "beginning of answer" token. + +Fuyu can also perform some question answering on natural images and charts/diagrams (thought fine-tuning may be required for good performance): +```python +text_prompt = "What color is the bus?\n" +url = "https://huggingface.co/adept/fuyu-8b/resolve/main/bus.png" +image = Image.open(requests.get(url, stream=True).raw) + +inputs = processor(text=text_prompt, images=image, return_tensors="pt").to("cuda:0") + +generation_output = model.generate(**inputs, max_new_tokens=6) +generation_text = processor.batch_decode(generation_output[:, -6:], skip_special_tokens=True) +assert generation_text == ["The bus is blue.\n"] + + +text_prompt = "What is the highest life expectancy at birth of male?\n" +url = "https://huggingface.co/adept/fuyu-8b/resolve/main/chart.png" +image = Image.open(requests.get(url, stream=True).raw) + +model_inputs = processor(text=text_prompt, images=image, return_tensors="pt").to("cuda:0") + +generation_output = model.generate(**model_inputs, max_new_tokens=16) +generation_text = processor.batch_decode(generation_output[:, -16:], skip_special_tokens=True) +assert generation_text == ["The life expectancy at birth of males in 2018 is 80.7.\n"] +``` +For best performance, it's recommended to end questions with `\n`, as shown above! + +## Uses + +### Direct Use + +The model is intended for research purposes only. +**Because this is a raw model release, we have not added further finetuning, postprocessing or sampling strategies to control for undesirable outputs. You should expect to have to fine-tune the model for your use-case.** + +Possible research areas and tasks include + +- Applications in computer control or digital agents. +- Research on multi-modal models generally. + +Excluded uses are described below. + +### Out-of-Scope Use + +The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. + +## Limitations and Bias + +### Limitations + +- Faces and people in general may not be generated properly. + +### Bias +While the capabilities of these models are impressive, they can also reinforce or exacerbate social biases. \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..19c0095 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "|ENDOFTEXT|": 71013 +} diff --git a/architecture.png b/architecture.png new file mode 100644 index 0000000..a4116ea Binary files /dev/null and b/architecture.png differ diff --git a/bus.png b/bus.png new file mode 100644 index 0000000..8994abc Binary files /dev/null and b/bus.png differ diff --git a/chart.png b/chart.png new file mode 100644 index 0000000..332b68d Binary files /dev/null and b/chart.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..d3499d6 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "FuyuForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 71013, + "hidden_act": "relu2", + "hidden_dropout": 0.0, + "hidden_size": 4096, + "image_size": 300, + "initializer_range": 0.02, + "intermediate_size": 16384, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 16384, + "model_type": "fuyu", + "num_attention_heads": 64, + "num_channels": 3, + "num_hidden_layers": 36, + "partial_rotary_factor": 0.5, + "patch_size": 30, + "qk_layernorm": true, + "rope_scaling": null, + "rope_theta": 25000.0, + "text_config": { + "model_type": "persimmon" + }, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.0.dev0", + "use_cache": true, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9f76a78 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 71013, + "transformers_version": "4.35.0.dev0" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..f7d392b --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0360c23415254b77cf052e5dc5b57ecd98f28d65e1e4cb7a222c9fa35e97c0e +size 9934219312 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..3fbcb84 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb67849dfa2f360d8bf653386a3cbc36002b8921de62f9916f70872ab929e3eb +size 8882334152 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3c3f26d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,589 @@ +{ + "metadata": { + "total_size": 18816477184 + }, + "weight_map": { + "language_model.lm_head.weight": "model-00002-of-00002.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "language_model.model.final_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.final_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.16.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.17.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.18.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.19.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.30.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.31.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.32.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.33.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.34.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.input_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.post_attention_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.dense.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.dense.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.k_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.q_layernorm.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.query_key_value.bias": "model-00002-of-00002.safetensors", + "language_model.model.layers.35.self_attn.query_key_value.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_layernorm.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.query_key_value.bias": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.query_key_value.weight": "model-00001-of-00002.safetensors", + "vision_embed_tokens.bias": "model-00002-of-00002.safetensors", + "vision_embed_tokens.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..1a4775b --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,8 @@ +{ + "image_processor_type": "FuyuImageProcessor", + "padding_mode": "constant", + "padding_value": 1.0, + "processor_class": "FuyuProcessor", + "target_height": 1080, + "target_width": 1920 +} diff --git a/skateboard.png b/skateboard.png new file mode 100644 index 0000000..3a3b084 Binary files /dev/null and b/skateboard.png differ diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..27217b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,9 @@ +{ + "additional_special_tokens": [ + "", + "|ENDOFTEXT|" + ], + "bos_token": "|ENDOFTEXT|", + "eos_token": "|ENDOFTEXT|", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c55a652 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20119416a890c3fefc86210999fb8189dde194c12f7f861dbb3bc7a922baaabb +size 16454569 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..1f9e5bf --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407d001d18582959881b30ff39b660d4bd5ee50957d03f57daeeb3059e9db54c +size 6128796 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..823efb7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71013": { + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "|ENDOFTEXT|" + ], + "bos_token": "|ENDOFTEXT|", + "clean_up_tokenization_spaces": false, + "eos_token": "|ENDOFTEXT|", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "processor_class": "FuyuProcessor", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}