Upload the model

.gitattributes

@@ -33,4 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-split_part_* filter=lfs diff=lfs merge=lfs -text
+ckpts/* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,30 @@
 ---
-license: apache-2.0
+license: other
+license_name: cogvlm2
+license_link: https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B/blob/main/LICENS
+
+language:
+- ens
+pipeline_tag: text-generation
+tags:
+- chat
+- cogvlm2
+
+inference: false
 ---
+# VisionReward-Image
+
+## Introduction
+We present VisionReward, a general strategy to aligning visual generation models——both image and video generation——with human preferences through a fine-grainedand multi-dimensional framework. We decompose human preferences in images and videos into multiple dimensions,each represented by a series of judgment questions, linearly weighted and summed to an interpretable and accuratescore. To address the challenges of video quality assess-ment, we systematically analyze various dynamic features of videos, which helps VisionReward surpass VideoScore by 17.2% and achieve top performance for video preference prediction.
+Here, we present the model of VisionReward-Image.
+
+## Merging and Extracting Checkpoint Files
+Use the following command to merge the split files into a single `.tar` file and then extract it into the specified directory:
+
+```sh
+cat ckpts/split_part_* > ckpts/visionreward_image.tar
+tar -xvf ckpts/visionreward_image.tar
+```
+
+## Using this model
+You can quickly install the Python package dependencies and run model inference in our [github](https://github.com/THUDM/VisionReward).

ckpts/split_part_aa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b17eb0d861c70dab3e6226cdacc3bfea8eb59feb897f8728152f5bdb6afd5e
+size 5221908480

ckpts/split_part_ab

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db459381667c7d5bb35a1cada7ce74387924e6397c2b8ee16d6d9f6b0939dc6c
+size 5221908480

ckpts/split_part_ac

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e6b652af3ef13bb2d15c23f2ee2d31c97916686dbe43788dd23fe42723704e
+size 5221908480

ckpts/split_part_ad

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3991f16bd6dd917088c5a869dffe9f993879b687412afe934d2b30063d2749
+size 5221908480

ckpts/split_part_ae

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fb496a7a83cb6df4cd728cafc3c058c296bbaaa1d2efc943cec9b1982a7850
+size 5221908480

ckpts/split_part_af

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b479a4e489269868e7734c03bd20f4bcad75c74244ece15fcf759faf0c7e443c
+size 5221908480

ckpts/split_part_ag

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fa73a5cacf6254ac7eb4a536cdd93231474c1aeb93930a15adacb470da77ef
+size 5221908480

ckpts/split_part_ah

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d377163aac293220b3ee49b85c0c5698de9af70e0197b7c27e52145066b1f6
+size 5221908480

ckpts/split_part_ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1afa5c84efed4e4e03f96d77f31c7a08a4b17c0197f941d962a961ecabeb00
+size 5221908480

ckpts/split_part_aj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a44c61804c077ff9df1023fded4b40084cc1dd4c8ad0fc9d2aa00e88e04c214
+size 5221908480

ckpts/split_part_ak

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de84a206568f4aaef88defc77166b46fb9c6c2b6e9358f9dd5f4d1f3907b4f27
+size 5221908480

ckpts/split_part_al

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19506291b67359369c4f4222c596314ee32c826d3df1f6d92242dd8d432362f
+size 5221908480

ckpts/split_part_am

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35dcc0a761dbb854f25fc1bedeeffa2315542b71a6c01c269572e11b916bf548
+size 5221908480

ckpts/split_part_an

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182e41c50e7a7233e831e43fb9e717ed97357339446d1d85852b6cf3997316ca
+size 5221908480

ckpts/split_part_ao

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e74b4bc0d5c976ea441a68aec3a05f920c1ed6724c0c719911f553df7d9c94
+size 4906260480

latest

@@ -0,0 +1 @@
+1

model_config.json

@@ -0,0 +1,41 @@
+{
+    "model_class": "VisualChatModel",
+    "tokenizer_type": "Meta-Llama-3-8B-Instruct",
+    "num_layers": 32,
+    "hidden_size": 4096,
+    "num_attention_heads": 32,
+    "vocab_size": 128256,
+    "layernorm_order": "pre",
+    "model_parallel_size": 1,
+    "max_sequence_length": 8192,
+    "use_bias": false,
+    "inner_hidden_size": 14336,
+    "num_multi_query_heads": 8,
+    "image_length": 2304,
+    "image_size": 1344,
+    "eva_args": {
+        "model_class": "EVA2CLIPModel",
+        "num_layers": 63,
+        "hidden_size": 1792,
+        "num_attention_heads": 16,
+        "vocab_size": 1,
+        "layernorm_order": "post",
+        "model_parallel_size": 1,
+        "max_sequence_length": 257,
+        "inner_hidden_size": 15360,
+        "use_final_layernorm": false,
+        "layernorm_epsilon": 1e-06,
+        "row_parallel_linear_final_bias": false,
+        "image_size": [
+            1344,
+            1344
+        ],
+        "pre_len": 1,
+        "post_len": 0,
+        "in_channels": 3,
+        "patch_size": 14
+    },
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "pad_token_id": null
+}