Update tiny models for Dots1ForCausalLM

.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 @@
+{% if messages[0]['role'] == 'system' %}<|system|>{{ messages[0]['content'] }}<|endofsystem|>{% set start_idx = 1 %}{% else %}<|system|><|endofsystem|>{% set start_idx = 0 %}{% endif %}{% for idx in range(start_idx, messages|length) %}{% if messages[idx]['role'] == 'user' %}<|userprompt|>{{ messages[idx]['content'] }}<|endofuserprompt|>{% elif messages[idx]['role'] == 'assistant' %}<|response|>{{ messages[idx]['content'] }}<|endofresponse|>{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] == 'user' %}<|response|>{% endif %}

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "Dots1ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "first_k_dense_replace": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 512,
+  "max_window_layers": 62,
+  "model_type": "dots1",
+  "moe_intermediate_size": 16,
+  "n_group": 1,
+  "n_routed_experts": 8,
+  "n_shared_experts": 1,
+  "norm_topk_prob": false,
+  "num_attention_heads": 2,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 151659
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 151643,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 151643,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cda3bb9818f075df194c886f19b995c3813d4f97ad86bde4d0d76e36fbb943f
+size 38979728

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ba517a1e51f2ff426ce80d747c0982b05fba551278ecb9f572b55e2664ce5d
+size 11420760

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|userprompt|>",
+    "<|endofuserprompt|>",
+    "<|response|>",
+    "<|endofresponse|>",
+    "<|system|>",
+    "<|endofsystem|>",
+    "<|observation|>",
+    "<|endofobservation|>",
+    "<|execution|>",
+    "<|endofexecution|>",
+    "<|reject-unknown|>",
+    "<|sec-cot|>",
+    "<|sec-end-cot|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}