Upload checkpoints

README.md

@@ -0,0 +1,12 @@
+---
+inference: false
+---
+
+# Model Card
+
+Bunny is a family of lightweight multimodal models.
+
+Bunny-stablelm-2-eva-lora leverages StableLM-2 as the language model backbone and EVA-CLIP 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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "stabilityai/stablelm-2-1_6b",
+  "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": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06802abe1589b62f5d1826bb43fd8204a63575cfa3e1fcb3fb471e9ec1daa34
+size 242266824

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bunny-stablelm-2-eva-lora",
+  "architectures": [
+    "StableLMEpochForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "bunny_stablelm.BunnyStableLMConfig",
+    "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
+  },
+  "bos_token_id": null,
+  "eos_token_id": 100257,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_vision_tower": "/path/to/EVA02_CLIP_L_336_psz14_s6B.pt",
+  "model_type": "bunny-stablelm",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "rope_pct": 0.25,
+  "rope_theta": 10000,
+  "rotary_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_qkv_bias": true,
+  "vocab_size": 100352
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f1b4ac0b5bbe2ede0f67d8b187533477e21bf1133c5d131a8538eb32e61968
+size 12593328