Update tiny models for Ernie4_5_MoeModel

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if not add_generation_prompt is defined -%}
+    {%- set add_generation_prompt = true -%}
+{%- endif -%}
+{%- if not cls_token is defined -%}
+    {%- set cls_token = "<|begin_of_sentence|>" -%}
+{%- endif -%}
+{%- if not sep_token is defined -%}
+    {%- set sep_token = "<|end_of_sentence|>" -%}
+{%- endif -%}
+{{- cls_token -}}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {{- "User: " + message["content"] + "
+" -}}
+    {%- elif message["role"] == "assistant" -%}
+        {{- "Assistant: " + message["content"] + sep_token -}}
+    {%- elif message["role"] == "system" -%}
+        {{- message["content"] + "
+" -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "Assistant: " -}}
+{%- endif -%}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Ernie4_5_MoeModel"
+  ],
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 512,
+  "model_type": "ernie4_5_moe",
+  "moe_intermediate_size": 16,
+  "moe_k": 2,
+  "moe_layer_end_index": 1,
+  "moe_layer_interval": 1,
+  "moe_layer_start_index": 0,
+  "moe_norm_min": 1e-12,
+  "moe_num_experts": 8,
+  "moe_num_shared_experts": 2,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_bias": false,
+  "use_cache": true,
+  "vocab_size": 101304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898fc7d4f2d3723d190f7f9c9905a01645956978ee5cd2e4425e8d5345a3155a
+size 13133040

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5b4d49475d27c7ef7a61eea2d675f9cc013e91e3ddb5e06d964f5027c1814a
+size 11185815

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|begin_of_sentence|>",
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "mask_token": "<mask:1>",
+  "model_max_length": 512,
+  "pad_token": "<unk>",
+  "sep_token": "<|end_of_sentence|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}