Upload model weights

README.md

@@ -1,3 +1,17 @@
 ---
+inference: false
 license: apache-2.0
 ---
+
+# Model Card
+
+Bunny is a family of lightweight multimodal models.
+
+Bunny-qwen1.5-1.8b-siglip-lora leverages Qwen1.5-1.8B as the language model backbone and SigLIP as the vision encoder.
+It is pretrained on LAION-2M and finetuned on Bunny-695K.
+
+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.

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69f3e146c07e3bb8f218cee1d84d565c05790b8692054b436a624c7d099decb
+size 239907520

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bunny-qwen1.5-1.8b-siglip-lora",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "mm_hidden_size": 1152,
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "model_type": "bunny-qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3575c748c643c9571c3cd44f533cadea7ba19103c34d689797e820899ee8e78a
+size 13117616