Upload checkpoints

README.md

@@ -1,3 +1,17 @@
 ---
+inference: false
 license: apache-2.0
 ---
+
+# Model Card
+
+Bunny is a family of lightweight multimodal models.
+
+Bunny-minicpm-siglip-lora leverages MiniCPM-2B 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": "/share/bunny/models/MiniCPM_step280000",
+  "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": [
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2dc8a16e74c586d722dc77fac8c3fd1c98ae1cb7ba59273bb6f451276a5de7
+size 436546336

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bunny-minicpm-siglip-lora",
+  "architectures": [
+    "MiniCPMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_minicpm.MiniCPMConfig",
+    "AutoModel": "modeling_minicpm.MiniCPMModel",
+    "AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM",
+    "AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "dim_model_base": 256,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 2304,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.1,
+  "intermediate_size": 5760,
+  "max_position_embeddings": 2048,
+  "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-minicpm",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 36,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 122753
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b0010e5f1288147776f439f55701d9ef51f3bf0f191f56107ce992b39d30f0
+size 15936688