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: 64000
+            pos_embed_config:
+              type: PositionEmbedding
+              args:
+                n_embed: 768
+                n_pos: 2048
+            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: 2048
+                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: 64000
+        n_embed: 768
+        perform_transform: false
+        act_fn_config: null
+        ln_config: null

paddle_model.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c707cb5f4488f2efe42b1f9113e1bbb9486ada78d379e9ef1c6fc2aa4ffdb5d8
+size 543139202

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
+size 1071955

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "keep_accents": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": false,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "GPTSw3Tokenizer",
+  "unk_token": "<unk>"
+}