init

README.md

@@ -0,0 +1,17 @@
+---
+inference: false
+license: apache-2.0
+---
+
+# Model Card
+
+Bunny is a family of lightweight multimodal models.
+
+Bunny-pretrain-llama3-8b-siglip is the pretrained weights for [Bunny-Llama-3-8B-V](https://huggingface.co/BAAI/Bunny-Llama-3-8B-V), which leverages Llama-3-8B-Instruct as the language model backbone and SigLIP as the vision encoder.
+It is pretrained on LAION-2M.
+
+More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).
+
+# License
+This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses.
+The content of this project itself is licensed under the Apache license 2.0.

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bunny-pretrain-llama3-8b-siglip",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mm_hidden_size": 1152,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "model_type": "bunny-llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "tune_mm_mlp_adapter": true,
+  "unfreeze_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 128256
+}

mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0108fa6fb0f15d9ce0678e029d55ab09f571813d7b5db3593665c5570b6f2bc
+size 43010104