first commit

Browse files

Files changed (6) hide show

.gitattributes +1 -0
config.yaml +81 -0
paddle_model.pdparams +3 -0
special_tokens_map.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +191 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -0,0 +1,81 @@

+arch:
+  type: TransformerLMHeadModel
+  args:
+    transformer_config:
+      type: TransformerDecoderOnlyModel
+      args:
+        embed_config:
+          type: OPTEmbeddingBlock
+          args:
+            token_embed_config:
+              type: TokenEmbedding
+              args:
+                n_embed: 768
+                n_vocab: 50000
+            pos_embed_config:
+              type: OPTLearnedPositionalEmbedding
+              args:
+                n_pos: 2048
+                n_embed: 768
+                offset: 2
+            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: false
+                scale_layer_wise: false
+                layer_idx: null
+                perform_linear_bias: false
+                perform_bloom_split_head: false
+                perform_query_scaling: true
+                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: 50000
+        n_embed: 768
+        perform_transform: false
+        act_fn_config: null
+        ln_config: null

paddle_model.pdparams ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b57e45d0f16cb9022514c2cef363166be5744b50e1c4724098dd6d7c00e0841
+size 500137346

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,191 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[START_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[END_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[IMAGE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "</fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "</work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[START_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[END_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[START_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "[END_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "[START_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "[END_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "[START_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "[END_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "[START_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "[END_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "[START_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "[END_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}