first commit

.gitattributes

@@ -33,3 +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
+paddle_model.pdparams filter=lfs diff=lfs merge=lfs -text

config.yaml

@@ -0,0 +1,80 @@
+arch:
+  type: TransformerLMHeadModel
+  args:
+    transformer_config:
+      type: TransformerDecoderOnlyModel
+      args:
+        embed_config:
+          type: TransformerEmbeddingBlock
+          args:
+            token_embed_config:
+              type: TokenEmbedding
+              args:
+                n_embed: 768
+                n_vocab: 50257
+            pos_embed_config:
+              type: PositionEmbedding
+              args:
+                n_embed: 768
+                n_pos: 1024
+            type_embed_config: null
+            ln_config: null
+            p_drop_embed: 0.1
+            concat_strategy: id_first
+        decoder_config:
+          type: TransformerDecoderBlock
+          args:
+            attn_config:
+              type: MultiHeadKeyValueAttention
+              args:
+                n_embed: 768
+                n_pos: 1024
+                n_head: 12
+                head_size: 64
+                p_drop_attn: 0.1
+                p_drop_resid: 0.1
+                bias_attn: true
+                bias_proj: true
+                cross_attn: false
+                scale_dot_product: true
+                scale_layer_wise: false
+                layer_idx: null
+                perform_linear_bias: false
+                perform_bloom_split_head: false
+                perform_query_scaling: false
+                attn_window_size: null
+            mlp_config:
+              type: TransformerMLP
+              args:
+                n_embed: 768
+                n_inner: 3072
+                act_fn_config:
+                  type: NewGELUActivation
+                  args: {}
+                p_drop_mlp: 0.1
+            ln_config:
+              type: LayerNorm
+              args:
+                n_embed: 768
+                ln_eps: 1.0e-05
+            n_embed: 768
+            post_norm: false
+            add_cross_attn: false
+        n_embed: 768
+        n_layer: 12
+        n_head: 12
+        ln_config:
+          type: LayerNorm
+          args:
+            n_embed: 768
+            ln_eps: 1.0e-05
+        perform_linear_bias: false
+        attn_window_size_loop_unit: null
+    lm_head_config:
+      type: TransformerLMHead
+      args:
+        n_vocab: 50257
+        n_embed: 768
+        perform_transform: false
+        act_fn_config: null
+        ln_config: null

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}