Add ASASR weights: sr_lora, dpo_lora (AS-DPO), adv_lora (rank-16 AMG)

adv_lora/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*x_embedder|.*(?<!single_)transformer_blocks\\.[0-9]+\\.norm1\\.linear|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_k|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_q|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_v|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_out\\.0|.*(?<!single_)transformer_blocks\\.[0-9]+\\.ff\\.net\\.2|.*single_transformer_blocks\\.[0-9]+\\.norm\\.linear|.*single_transformer_blocks\\.[0-9]+\\.proj_mlp|.*single_transformer_blocks\\.[0-9]+\\.proj_out|.*single_transformer_blocks\\.[0-9]+\\.attn.to_k|.*single_transformer_blocks\\.[0-9]+\\.attn.to_q|.*single_transformer_blocks\\.[0-9]+\\.attn.to_v|.*single_transformer_blocks\\.[0-9]+\\.attn.to_out)",
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adv_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b93fff2e2318919bf80a9ec7c8f282fa6b5c0122a1f5460b4295ce48cb69492
+size 115994960

dpo_lora/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*x_embedder|.*(?<!single_)transformer_blocks\\.[0-9]+\\.norm1\\.linear|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_k|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_q|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_v|.*(?<!single_)transformer_blocks\\.[0-9]+\\.attn\\.to_out\\.0|.*(?<!single_)transformer_blocks\\.[0-9]+\\.ff\\.net\\.2|.*single_transformer_blocks\\.[0-9]+\\.norm\\.linear|.*single_transformer_blocks\\.[0-9]+\\.proj_mlp|.*single_transformer_blocks\\.[0-9]+\\.proj_out|.*single_transformer_blocks\\.[0-9]+\\.attn.to_k|.*single_transformer_blocks\\.[0-9]+\\.attn.to_q|.*single_transformer_blocks\\.[0-9]+\\.attn.to_v|.*single_transformer_blocks\\.[0-9]+\\.attn.to_out)",
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

dpo_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ee6248e984c121c78a17d629f8ba4ce8a7e1e99122f626d19555840c7604f2
+size 115994960

sr_lora/pytorch_lora_weights_v2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658f580b2e8c7517baefe99c3c37eef078cecd456a9acbfa982d94ed18f217ae
+size 927314072