Update tiny models for CwmForCausalLM

.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 +1,13 @@
+{% set loop_messages=messages %}{%- set ns=namespace(last_query_index=-1) %}{%- for message in loop_messages[::-1] %}{%- set index=(loop_messages|length-1)-loop.index0 %}{%- if message.role=='user' %}{%- set ns.last_query_index=index %}{%- break %}{%- endif %}{%- endfor %}{% for message in loop_messages %}{%- set loop_index=loop.index0 %}{%- set content=message['content']|trim %}{%- if message.role=='assistant' %}{%- set reasoning_content='' %}{%- if '<think>
+' in content and '</think>' in content %}{%- set reasoning_content=content.split('</think>')[0].split('<think>
+')[-1].strip() %}{%- set content=content.split('</think>')[-1].lstrip() %}{%- endif %}{%- if loop_index>ns.last_query_index or preserve_previous_think is not defined or preserve_previous_think is true %}{%- if loop_index==0 %}{{ bos_token }}{%- endif %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{%- if reasoning_content %}{{ '<think>
+' }}{{ reasoning_content }}{{ '</think>' }}{%- endif %}{{ content }}<|eot_id|>{%- else %}{%- if loop_index==0 %}{{ bos_token }}{%- endif %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{{ content }}<|eot_id|>{%- endif %}{%- else %}{%- if loop_index==0 %}{{ bos_token }}{%- endif %}<|start_header_id|>{{ message.role }}{{ '<|end_header_id|>
+
+' }}{{ content }}<|eot_id|>{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{%- if enable_thinking is not defined or enable_thinking is true %}{{ '<think>
+' }}{%- endif %}{%- endif %}

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "CwmForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128001,
+  "head_dim": 16,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "cwm",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 16.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 1000000.0,
+    "rope_type": "llama3"
+  },
+  "sliding_window": 8192,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11df50ba574c0b177592a0cc4a44d009e6d7219f0c8f5e204d2c356ddd42dd5e
+size 32893752

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce6c1030d1247437cf3e2d197c37f3ab4dad08113c7a9956dae6db15479e0eb
+size 17208464

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "tokenizer_class": "TokenizersBackend"
+}