model ckpt upload

README.md

@@ -1,3 +1,19 @@
 ---
 license: mit
 ---
+
+This repository contains the baseline model of Conversation Speaker Idenfication as described in paper **Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding**.
+
+## Related Resources:
+- Paper: [Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding](to update)
+- Dataset: [Friends-MMC](https://huggingface.co/datasets/wangyueqian/friends_mmc)
+
+## Citation
+If you use this work in your research, please cite (to update):
+```
+@inproceedings{wang2025friends-mmc,
+  title={Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding},
+  author={Yueqian Wang and Xiaojun Meng and Yuxuan Wang and Jianxin Liang and Qun Liu and Dongyan Zhao},
+  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
+  year={2025}
+}

cnn/ft-5_turns/best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3ae7027d8a30aad11ff12d287beecf6af1302fd598f2c52194af93cfee6dcc
+size 94321627

cnn/ft-8_turns/best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160f55305eac9224b72322d5aed14ad47caf03587a802d3b8352a1a115523b21
+size 94321627

deberta/ft-5_turns/checkpoint-valid/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "./snap/multiturn/dialog_roberta-contrastive/0918-ijcai2019-mse_sim-deberta_large/checkpoint-valid",
+  "architectures": [
+    "DebertaV2ForSpeakerLabeling"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "sim_func": "linear",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

deberta/ft-5_turns/checkpoint-valid/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229e7ed6a445f7ed3db2e41fc7a18be91a3a14c6fcd62f317fab82b0265ce6a9
+size 1753508351

deberta/ft-8_turns/checkpoint-valid/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "./snap/multiturn/dialog_roberta-contrastive/0918-ijcai2019-mse_sim-deberta_large/checkpoint-valid",
+  "architectures": [
+    "DebertaV2ForSpeakerLabeling"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "sim_func": "linear",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

deberta/ft-8_turns/checkpoint-valid/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5f5be57fbf54c9ac197bfb6d3f2ce2a6ab315939565ffc2f80cf258f273eb7
+size 1753508351

deberta/pt-ijcai2019/checkpoint-valid/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/share2/wangyq/.cache/huggingface/transformers/microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSpeakerLabeling"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "sim_func": "linear",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

deberta/pt-ijcai2019/checkpoint-valid/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890dc7956944c8ddd9d0c4f9ed2af21de478a6581255ad5294c2f1316f91218c
+size 1753508351