Upload NeuroThinker custom checkpoint (63MB safetensors)

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|answer|>": 50259,
+  "<|end|>": 50260,
+  "<|prompt|>": 50257,
+  "<|think|>": 50258
+}

config.json

@@ -1,33 +1,19 @@
 {
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "dtype": "float32",
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 256,
-  "n_embd": 192,
-  "n_head": 3,
-  "n_inner": null,
-  "n_layer": 3,
-  "n_positions": 256,
+  "vocab_size": 50261,
+  "d_model": 384,
+  "n_layers": 6,
+  "n_heads": 6,
+  "d_head": 64,
+  "d_ff": 720,
+  "d_memory": 192,
+  "max_seq_len": 256,
+  "dropout": 0.1,
+  "rope_theta": 10000.0,
+  "memory_decay_init": 0.99,
+  "surprise_threshold": 0.1,
+  "rms_norm_eps": 1e-06,
   "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,
-  "transformers_version": "4.57.3",
-  "use_cache": true,
-  "vocab_size": 50257
-}
+  "bos_token_id": 50256,
+  "eos_token_id": 50260,
+  "model_type": "neurothinker"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4822217a8aa396213d653cc022d234dd0588dd26f895ed676b559ecaa1e3d615
-size 44137768
+oid sha256:c06d8248fbe1c975b80159d76b1b43ef6465b396467c8cb23739ea350478cf5b
+size 60979648

special_tokens_map.json

@@ -1,4 +1,34 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|prompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|answer|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "pad_token": "<|endoftext|>",

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -16,6 +11,42 @@
       "rstrip": false,
       "normalized": true,
       "special": true
+    },
+    {
+      "id": 50257,
+      "content": "<|prompt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50258,
+      "content": "<|think|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50259,
+      "content": "<|answer|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50260,
+      "content": "<|end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -8,8 +8,46 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50257": {
+      "content": "<|prompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|answer|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|prompt|>",
+    "<|think|>",
+    "<|answer|>",
+    "<|end|>"
+  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",