2601

src/sd15_2048.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057785145ba468215062bf2b6ea7dca9aa3186f0f010215eb00e4739bf213e17
-size 51250
+oid sha256:0e269bc293298ebb305b766c45576fc19bf7f5cbba3891f86fe0eb098941a6d9
+size 64886

test.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25096d7d566bf784726fbdbd762781a0ff0a25523554272c3c426989633dc969
-size 5145945
+oid sha256:58a27239863602451840062946b9930543b8b59bc0a7abaa59e613df0d216f2f
+size 5214545

text_encoder/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3bc4fb7ed18b75101464c8e6b93846ad0e626fa566592083d18866743d4893d
-size 1354
+oid sha256:84c37ee8025b892ca9210635a38228f4650373ad5e59628af66d344f967ce64e
+size 1360

text_encoder/generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9afb365eaab1c8fc2395f618067ee2307b9821e207f12c5c52cf371a14b0e0
+size 121

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbfc1bd7cdbaa8f0759d8d3c00d8a91bf9af50093fc3c7204c1e3e2c5fe3723
-size 3441183752
+oid sha256:08a190beb6e66815d00f15994ca740b1cbe78ee6f5b0c4d682855c9219451a5a
+size 3441185296

tokenizer/chat_template.jinja

@@ -1,7 +1,32 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
 {%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
+        {{- render_content(messages[0].content, false) + '\n\n' }}
     {%- endif %}
     {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
@@ -11,23 +36,22 @@
     {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
 {%- else %}
     {%- if messages[0].role == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+        {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|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 message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
-        {%- set ns.multi_step_tool = false %}
-        {%- set ns.last_query_index = index %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
     {%- endif %}
 {%- endfor %}
 {%- for message in messages %}
-    {%- if message.content is string %}
-        {%- set content = message.content %}
-    {%- else %}
-        {%- set content = '' %}
-    {%- endif %}
+    {%- set content = render_content(message.content, True) %}
     {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
         {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
@@ -82,8 +106,5 @@
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
-{%- endif %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

tokenizer/tokenizer_config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
+oid sha256:355f2b4e5bad7b01f11ef6cb68ebc176f61b95c3276092ea225b1bea0e01e95c
 size 5404

train.py

@@ -29,7 +29,7 @@ from transformers import AutoTokenizer, AutoModel
 # --------------------------- Параметры ---------------------------
 ds_path = "/workspace/sdxs/datasets/mjnj"
 project = "unet"
-batch_size = 48
+batch_size = 24
 base_learning_rate = 4e-5 #2.7e-5
 min_learning_rate = 1e-5 #2.7e-5
 num_epochs = 50

unet/config.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d4828222ad3a8cddeadf895d9a3afce5c95869d374458dc2c7e5d3b9bf9864
+oid sha256:526c074225e5cd6567d513a6fdfbbe27dacfe3580843229bcdcf66f229bfaa7f
 size 1813

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6caf99add90edb56022eadfc609bc34fae5be12b152fd7822f3d0ac57ff37703
-size 3566239360
+oid sha256:63bdfd6ba99237a331a64b494babcf5a1b463cad93178328e7e112f3c10488f3
+size 4663712768

unet_sd15/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d4828222ad3a8cddeadf895d9a3afce5c95869d374458dc2c7e5d3b9bf9864
+size 1813

unet_sd15/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117b50c39c48aab6471ffee83429331794f90b825bacda4488a2a4aa7ed2ffa8
+size 3566239360