updated model

README.md

@@ -1,3 +0,0 @@
----
-license: cc
----

config.json

@@ -1,14 +1,19 @@
 {
-  "_name_or_path": "/chronos_data/nisoni/analysing_hart_user_states/GPT2_TWT_PT_3June2024/outputs/gpt2_twt_pt_60bs",
+  "_name_or_path": "/chronos_data/nisoni/HaRT_Twt_model",
   "activation_function": "gelu_new",
+  "add_history": true,
   "architectures": [
-    "GPT2hlcLMHeadModel"
+    "HaRTPreTrainedModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "extract_layer": 11,
+  "freeze_model": false,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
+  "layer_ins": 2,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
@@ -17,24 +22,16 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 50256,
-  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
   "torch_dtype": "float32",
   "transformers_version": "4.33.1",
   "use_cache": true,
+  "use_hart_no_hist": false,
+  "use_qh05_wts": false,
   "vocab_size": 50258
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9018b546d98352c967aded0bc1e6626025839b8846c1a5184228eb6d101b29f2
-size 652200033
+oid sha256:593a35def4af82c3fa0546f068234c483766cc10005bb2acc3c8ef9f27c72b6f
+size 782895249

special_tokens_map.json

@@ -1,7 +1,6 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
   "sep_token": "<|insep|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,9 +1,33 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
   "model_max_length": 1024,
+  "pad_token": null,
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3480cd5758a54474a91ba1c798474a3993bf335537e6779a563a251720d2655b
+oid sha256:3822f8ccdb8783bf065a662eda9058a38704d232a74bd8a1eb90eccb80eb2003
 size 4091