Stage 1 checkpoint step 8000

.gitattributes

@@ -39,3 +39,4 @@ checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-8000/chat_template.jinja

@@ -0,0 +1,97 @@
+{{- '[@BOS@]\n' }}
+{%- if tools -%}
+<|start_of_turn|><|tool_declare|>
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+{{- '<|end_of_turn|>\n' }}{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif content is none -%}
+        {{- '' }}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|start_of_turn|><|user|>
+{{ visible_text(m.content) }}
+{{- '<|nothink|>' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("<|nothink|>")) else '' -}}
+{{- '<|end_of_turn|>\n' }}
+{%- elif m.role == 'assistant' -%}
+{{- '<|start_of_turn|><|assistant|>\n' }}
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{{- '<|end_of_turn|>\n' }}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|start_of_turn|><|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|start_of_turn|><|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+{{- '<|end_of_turn|>\n' }}{%- endif -%}
+{%- elif m.role == 'system' -%}
+<|start_of_turn|><|system|>
+{{ visible_text(m.content) }}
+{{- '<|end_of_turn|>\n' }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- '<|start_of_turn|><|assistant|>\n' }}
+{%- endif -%}

checkpoint-8000/config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 6,
+  "dtype": "float32",
+  "eos_token_id": 26,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 64,
+  "linear_num_key_heads": 12,
+  "linear_num_value_heads": 12,
+  "linear_value_head_dim": 64,
+  "max_position_embeddings": 2048,
+  "model_type": "qwen3_5_text",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-8000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 6,
+  "eos_token_id": 26,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

checkpoint-8000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2964d88c895ae3186fba1b4f7cf48e3aefbf5fcbb5fc6aba72d9e2ae5015c868
+size 1744703352

checkpoint-8000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a574ceaaff7c7a8f091179c53fd17ae33567089c099d4ff37d4cb3bc1a87e80e
+size 33627251

checkpoint-8000/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<|start_of_image|>",
+  "bos_token": "[@BOS@]",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<|end_of_image|>",
+  "eos_token": "<|end_of_turn|>",
+  "image_token": "<|image_soft_token|>",
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<|start_of_image|>",
+    "eoi_token": "<|end_of_image|>",
+    "image_token": "<|image_soft_token|>"
+  },
+  "pad_token": "<pad>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-8000/training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cff049421911517b816ca76f7aec6ab1c3a59179760c768dc3145b307b33f0
+size 3489605443