Upload checkpoints

README.md

@@ -0,0 +1,12 @@
+---
+inference: false
+---
+
+# Model Card
+
+Bunny is a family of lightweight multimodal models.
+
+Bunny-phi-1.5-siglip-lora leverages Phi-1.5 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).

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "susnato/phi-1_5_dev",
+  "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": [
+    "query_key_value",
+    "fc1",
+    "dense",
+    "fc2"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aeb34022d805bffee5f7bcb2754d2e1754d6090c801066b6969fb479f4a261
+size 201352544

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "bunny-phi-1.5-siglip-lora",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "mm_hidden_size": 1152,
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "model_type": "bunny-phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "partial_rotary_factor": 0.5,
+  "pretraining_tp": 1,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 51200
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15ba8b306361eeb950fd8b2d3ebc2cf82bedec84be54cd742c04547cf48a3bd
+size 13117616