Upload fine-tuned CLIP model

README.md

@@ -0,0 +1,18 @@
+---
+language: en
+license: mit
+tags:
+- clip
+- vision
+- text
+- multimodal
+---
+
+# Fine-tuned CLIP-ViT-bigG-14 Model
+
+This model is a fine-tuned version based on laion/CLIP-ViT-bigG-14-laion2B-39B-b160k.
+
+## Usage Method
+
+base_model = CLIPTextModelWithProjection.from_pretrained("Boynn/CLIP-ViT-bigG-14-laion2B-39B-b160k-sft")
+

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "Boynn/CLIP-ViT-bigG-14-laion2B-39B-b160k-sft",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "vocab_size": 49408
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b35e803b219864bbb4da8070a97bdb37384ee65f034d21bd19c9e6284cbe56
+size 2778702264