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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

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: 1024
+                n_vocab: 151936
+            pos_embed_config: null
+            type_embed_config: null
+            ln_config: null
+            p_drop_embed: 0.0
+            concat_strategy: id_first
+        decoder_config:
+          type: TransformerDecoderBlock
+          args:
+            attn_config:
+              type: LlamaAttention
+              args:
+                n_embed: 1024
+                n_pos: 32768
+                n_head: 16
+                n_key_value_head: 16
+                head_size: 64
+                p_drop_attn: 0.0
+                p_drop_resid: 0.0
+                bias_attn: true
+                bias_proj: false
+                cross_attn: false
+                scale_dot_product: true
+                scale_layer_wise: false
+                layer_idx: null
+                rope_config:
+                  type: MistralRotaryEmbedding
+                  args:
+                    head_size: 64
+                    n_pos: 32768
+                    base: 1.0e06
+                    scaling_type: null
+                    scaling_factor: null
+            mlp_config:
+              type: LlamaMLP
+              args:
+                n_embed: 1024
+                n_inner: 2816
+                act_fn_config:
+                  type: SiLUActivation
+                  args: {}
+            ln_config:
+              type: LlamaRMSNorm
+              args:
+                n_embed: 1024
+                ln_eps: 1.0e-06
+            n_embed: 1024
+            post_norm: false
+            add_cross_attn: false
+        n_embed: 1024
+        n_layer: 24
+        n_head: 16
+        ln_config:
+          type: LlamaRMSNorm
+          args:
+            n_embed: 1024
+            ln_eps: 1.0e-06
+        perform_linear_bias: false
+        attn_window_size_loop_unit: null
+    lm_head_config:
+      type: TransformerLMHead
+      args:
+        n_vocab: 151936
+        n_embed: 1024
+        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 sha256:501a0fe809672c0404c5753ecc18b5870bf2cfba61ca380c34bb55f59ba65505
+size 2478313708

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}