Update tiny models for Step3p7Model

chat_template.jinja

@@ -0,0 +1,89 @@
+{% macro render_message_content(message) %}{% if message.content is none %}{{- '' }}{% elif message.content is string %}{{- message.content }}{% elif message.content is mapping %}{{- message.content['value'] if 'value' in message.content else message.content['text'] }}{% elif message.content is iterable %}{% set ns = namespace(needs_text_separator=false) %}{% for item in message.content %}{% if item.type == 'text' %}{% if ns.needs_text_separator %}{{- ' ' }}{% endif %}{{- item['value'] if 'value' in item else item['text'] }}{% set ns.needs_text_separator = true %}{% elif item.type == 'image' %}<im_patch>{% set ns.needs_text_separator = false %}{% endif %}{% endfor %}{% endif %}{% endmacro %}
+{{bos_token}}{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_effort is defined %}
+        {{- "Reasoning: " + reasoning_effort + '\n\n' }}
+    {%- endif %}
+    {%- if messages[0].role == 'system' %}
+        {{- render_message_content(messages[0]) + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions in JSONSchema format:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson(ensure_ascii=False) }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...>\n...\n</function> block must be nested within <tool_call>\n...\n</tool_call> XML tags\n- Required parameters MUST be specified\n</IMPORTANT><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if reasoning_effort is defined %}
+            {{- "Reasoning: " + reasoning_effort + '\n\n' }}
+        {%- endif %}
+        {{- render_message_content(messages[0]) + '<|im_end|>\n' }}
+    {%- elif reasoning_effort is defined %}
+        {{- '<|im_start|>system\n' + "Reasoning: " + reasoning_effort + '\n\n' + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and render_message_content(message) is string and not(render_message_content(message).startswith('<tool_response>') and render_message_content(message).endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_message_content(message) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {%- set role_name = 'observation' if (message.role == "system" and not loop.first and message.name == 'observation') else message.role %}
+        {{- '<|im_start|>' + role_name + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.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') %}
+            {%- else %}
+                {%- set reasoning_content = '' %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- if tool_call.arguments is defined %}
+                    {%- set arguments = tool_call.arguments | fromjson if tool_call.arguments is string else tool_call.arguments %}
+                    {%- for args_name, args_value in arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson(ensure_ascii=False) | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>tool_response\n' }}
+        {%- endif %}
+        {{- '<tool_response>' }}
+        {{- content }}
+        {{- '</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "Step3p7Model"
+  ],
+  "dtype": "float32",
+  "image_token_id": 4,
+  "model_type": "step3p7",
+  "pad_token_id": 1,
+  "projector_bias": false,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 128007,
+    "head_dim": 8,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 200,
+    "mlp_bias": false,
+    "mlp_layer_types": [
+      "dense",
+      "sparse"
+    ],
+    "model_type": "step3p5",
+    "moe_intermediate_size": 8,
+    "moe_router_scaling_factor": 1.0,
+    "mtp_layer_types": null,
+    "mtp_mlp_layer_types": null,
+    "n_routed_experts": 4,
+    "num_attention_heads": 2,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "num_nextn_predict_layers": 0,
+    "num_sliding_attention_heads": 2,
+    "pad_token_id": 1,
+    "per_layer_config": {},
+    "query_pre_attn_scalar": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "share_expert_dim": 8,
+    "sliding_window": 64,
+    "swiglu_limits": null,
+    "swiglu_limits_shared": null,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 128815
+  },
+  "transformers_version": "5.19.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 8,
+    "image_size": 16,
+    "intermediate_size": 8,
+    "layer_norm_eps": 1e-05,
+    "layer_scale_init_value": 0.1,
+    "max_position_embeddings": 2704,
+    "mlp_ratio": 1.0,
+    "model_type": "step3p5_vision",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 1,
+    "patch_size": 4,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "axial"
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05ee98debab7c2f72cc64a4de015f0ee9509b7d3c3d39a2ce628c72edae88ca
+size 8301400

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}