Upload folder using huggingface_hub

chat_template.jinja

@@ -20,7 +20,7 @@ You may call one or more functions to assist with the user query.
 You are provided with function signatures within <tools></tools> XML tags:
 <tools>
 {% for tool in tools %}
-{%- if 'function' in tool -%}
+{%- if tool is not none and tool is mapping and 'function' in tool -%}
     {%- set tool = tool['function'] -%}
 {%- endif -%}
 {% if tool.defer_loading is not defined or not tool.defer_loading %}
@@ -48,7 +48,7 @@ For each function call, output the function name and arguments within the follow
 {%- endmacro -%}
 {%- set ns = namespace(last_user_index=-1, thinking_indices='') -%}
 {%- for m in messages %}
-    {%- if m.role == 'user' %}
+    {%- if m is not none and m is mapping and m.role == 'user' %}
         {%- set ns.last_user_index = loop.index0 -%}
     {%- elif m.role == 'assistant' %}
         {%- if m.reasoning_content is string %}
@@ -58,7 +58,7 @@ For each function call, output the function name and arguments within the follow
 {%- endfor %}
 {%- set ns.has_thinking = false -%}
 {%- for m in messages -%}
-{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}
+{%- if m is not none and m is mapping and m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}
 {%- elif m.role == 'assistant' -%}
 <|assistant|>
 {%- set content = visible_text(m.content) %}
@@ -98,10 +98,10 @@ For each function call, output the function name and arguments within the follow
     {{- '<tool_response><tools>\n' -}}
     {% for tr in m.content %}
         {%- for tool in tools -%}
-            {%- if 'function' in tool -%}
+            {%- if tool is not none and tool is mapping and 'function' in tool -%}
                 {%- set tool = tool['function'] -%}
             {%- endif -%}
-            {%- if tool.name == tr.name -%}
+            {%- if tool is not none and tool is mapping and tool.name == tr.name -%}
                 {{- tool_to_json(tool) + '\n' -}}
             {%- endif -%}
         {%- endfor -%}

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "dtype": "bfloat16",
+  "torch_dtype": "bfloat16",
   "eos_token_id": [
     154820,
     154827,
@@ -13,7 +13,6 @@
   "ep_size": 1,
   "first_k_dense_replace": 3,
   "hidden_act": "silu",
-  "head_dim": 64,
   "hidden_size": 6144,
   "index_head_dim": 128,
   "index_n_heads": 32,
@@ -23,9 +22,89 @@
   "intermediate_size": 12288,
   "kv_lora_rank": 512,
   "max_position_embeddings": 202752,
+  "mlp_layer_types": [
+    "dense",
+    "dense",
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm_moe_dsa",
   "moe_intermediate_size": 2048,
   "moe_layer_freq": 1,
-  "model_type": "glm_moe_dsa",
   "n_group": 1,
   "n_routed_experts": 256,
   "n_shared_experts": 1,
@@ -35,7 +114,7 @@
   "num_hidden_layers": 78,
   "num_key_value_heads": 64,
   "num_nextn_predict_layers": 1,
-  "pad_token_id": 154820,
+  "pad_token_id": 154821,
   "pretraining_tp": 1,
   "q_lora_rank": 2048,
   "qk_head_dim": 256,
@@ -52,8 +131,9 @@
   "tie_word_embeddings": false,
   "topk_group": 1,
   "topk_method": "noaux_tc",
-  "transformers_version": "5.4.0",
+  "transformers_version": "5.6.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "v_head_dim": 256,
   "vocab_size": 154880
-}
+}

tokenizer_config.json

@@ -1,5 +1,6 @@
 {
   "backend": "tokenizers",
+  "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "<|endoftext|>",
@@ -26,8 +27,10 @@
   "is_local": true,
   "model_max_length": 202752,
   "model_specific_special_tokens": {},
-  "pad_token": "<|endoftext|>",
+  "pad_token": "[MASK]",
   "padding_side": "left",
   "remove_space": false,
-  "tokenizer_class": "TokenizersBackend"
-}
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n    {%- set ns_tool = namespace(first=true) -%}\n    {{ '{' -}}\n    {%- for k, v in tool.items() -%}\n        {%- if k != 'defer_loading' and k != 'strict' -%}\n            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n            {%- set ns_tool.first = false -%}\n            \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- '}' -}}\n{%- endmacro -%}\n<|system|>\n# 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>\n{% for tool in tools %}\n{%- if tool is not none and tool is mapping and 'function' in tool -%}\n    {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n    {%- if content is string -%}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if item is mapping and item.type == 'text' -%}\n                {{- item.text }}\n            {%- elif item is string -%}\n                {{- item }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{- content }}\n    {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1, thinking_indices='') -%}\n{%- for m in messages %}\n    {%- if m is not none and m is mapping and m.role == 'user' %}\n        {%- set ns.last_user_index = loop.index0 -%}\n    {%- elif m.role == 'assistant' %}\n        {%- if m.reasoning_content is string %}\n            {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- set ns.has_thinking = false -%}\n{%- for m in messages -%}\n{%- if m is not none and m is mapping and m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n    {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n    {%- set content = content.split('</think>')[-1] %}\n{%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %}\n    {%- set reasoning_content = '' %}\n{%- elif loop.index0 < ns.last_user_index and ns.has_thinking %}\n    {%- set reasoning_content = '' %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content +  '</think>'}}\n{%- else -%}\n{{ '</think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n    {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% 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 %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n    {{- '<|observation|>' -}}\n{%- endif %}\n{%- if m.content is string -%}\n    {{- '<tool_response>' + m.content + '</tool_response>' -}}\n{%- else -%}\n    {{- '<tool_response><tools>\\n' -}}\n    {% for tr in m.content %}\n        {%- for tool in tools -%}\n            {%- if tool is not none and tool is mapping and 'function' in tool -%}\n                {%- set tool = tool['function'] -%}\n            {%- endif -%}\n            {%- if tool is not none and tool is mapping and tool.name == tr.name -%}\n                {{- tool_to_json(tool) + '\\n' -}}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- endfor -%}\n    {{- '</tools></tool_response>' -}}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}\n{%- endif -%}"
+}