Add files using upload-large-folder tool

.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 +1,86 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+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 %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<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 -%}
+{%- 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 -%}
+    {%- 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' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- 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 ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<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 %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "Glm4MoeLiteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "pad_token_id": 154820,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 202752,
+  "model_type": "glm4_moe_lite",
+  "moe_intermediate_size": 1536,
+  "topk_method": "noaux_tc",
+  "norm_topk_prob": true,
+  "num_attention_heads": 20,
+  "n_group": 1,
+  "topk_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 1,
+  "routed_scaling_factor": 1.8,
+  "num_experts_per_tok": 4,
+  "first_k_dense_replace": 1,
+  "num_hidden_layers": 47,
+  "num_key_value_heads": 20,
+  "num_nextn_predict_layers": 1,
+  "partial_rotary_factor": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "dtype": "bfloat16",
+  "transformers_version": "5.0.0rc0",
+  "q_lora_rank": 768,
+  "kv_lora_rank": 512,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90abe0d075755853145c96906a1300f57c167fcc9aa67221239b448abf54933c
+size 1438134344

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c51e2434efe609cbe652014a924e088a5ea97be35ca29cfa893a1a9a90304b1
+size 1270648128

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6ebdd01af10c9bde1ec0b2a182d6f7ff8df831add6810695e5f3b50918040d
+size 1270648128

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e4dbb8f7583d2b6392a6e850dd7aa05636827e8b90ff7858cae709838dca7
+size 1270648128

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f56a3e52bf5905c2df07ef53575ae8e62622138a15b0affc2b3f84785ca81e9
+size 1270648128

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83aa0eeca6e5a9394bb8a1c9cab46cc603799d729cf64ed4bbc341e0a7085feb
+size 1270648128

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9679076d3bd10c5f1287d12418fddb41c8b54b8c8ccc0672796ef7e8431b797
+size 1270648128

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1231577a057ff957d480c277e497910acbba75fc9232f8fd8f44c1a647d7a2
+size 1270648128

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095d626626773284535ba4114c2b320003ba3c8430bd104f5e7bba3772b2a1b1
+size 1270648128

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f8d197b0d253082f547d67989b1e3928a742b508f6f8d4abf119f3ba2990ed
+size 1270648128

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b7eeef625a6ed9ced479e064870f0ebf0da67056cd5e582300d0ebcf44de21
+size 1270648328

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49adb8b9f02d1643ab22406b0e05938ce3d7a8986fd0981e0af5d4cd47ee8b12
+size 1270648328

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f269382ae6ce42cd05937fcd5551e08da151c810a87bb0e1994ff9bb5f9eb7c9
+size 1270648328

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd6f36aadceda658a5db6fc6a04160ae2ca1ae78d4a9c84aeabcea8e80b44c8
+size 1270648328

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53fb45f7689b505fc185180503ea9d45af67042ba38914e53bbdee97173c974
+size 1270648328

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51e478badd50bb9b5299e3ad7979bfd40da8ab96983de0cd16a0fb5fddb4bc9
+size 1270648328

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680295c83f29a90c97f2d68c1290a152330c2dbd3654abdf0f074e6d8018062c
+size 1270648328

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:355f9437e291b0846b5ecac1d644766ec17bd4863da441e4e786f33d7bac3347
+size 1270648328

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111570fc7f55bcb9beb7bcb969475b27ffbcad97b95788464ff91a1e07ff897a
+size 1270648328

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced6a73df393df3bd559fc69093763fb5cc9fedee31e245a52a7786939199896
+size 1270648328

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b287bb0ce12a1ac975978c94548f2bbab3267e83e0c888871a3ada3ddf91405d
+size 1270648328

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e77476f0f57dc0386b64741d9251632d46e646faab6780d10a5a6a5f456668
+size 1270648328

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9e643d9d3e9152b9156424615c8054cffe6b8bc1b776567da17bbd3b97ebcb
+size 1270648328

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634da561277b9b77410a319bd930e940d443055fb688a2e4b9574aae1569192d
+size 1270648328

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6591dfb36a59918f91c152ba0baf184b4372c667fe46f74024e5d8ae86f378
+size 1270648328

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62373b800980841e6ca5c4c48db570729246092d03ac756bdeb55ecfdd599a2c
+size 1270648328

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332d82cefb0b4d87c48e3e989c97d3e74b6f64326313694ed226a72bf26e3b99
+size 1270648328

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9897915eef55f41b221ff072d8b0b401e447007d648b63ddabf9b795361c18
+size 1270648328

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29059fb79e6fefaad49b7c2833370cd78079b403cc98bc28ce95976207840f7f
+size 1270648328

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f989cc8af19949a310599c5ab8d65f0ae8406908e1a702588b892604179061a1
+size 1270648328

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa91e9b1a075d1753e45a01db198ed48f2739392e46e1843a4dcaaab6cd02eb
+size 1270648328

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf807da31533424a54196cd07da6caa1a22199b72d822bd8c2f387172b6e1c65
+size 1270648328

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887aeb5568ef6189a7618309e50f0277ad339da86133526ca6d820b88ecbb5d4
+size 1270648328

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036a38cc10858a8cc5a2fcd09fdab1b53258d04ff87dc4d3d21f140c54b029dd
+size 1270648328

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ae341291fe720719ab6cdcf2348752f262f4575a3f8221b353deb224bcbd1d
+size 1270648328

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8af33462a3f7b4dbc5393da4016acffabafc20b826f952e912adb2a2845fe3
+size 1270648328

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39098c9b6770ff5c185a70b8f0d6cfca22f95e3c47dc38de88c3d2ec2b1cf5bc
+size 1270648328

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe0b23aab19b608ca59f46628064c3d53d846c81d6f978c2579b38e09e35747
+size 1270648328

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe1da68f8c30d7e77a68d48eb7d65d28709f536062dba8168490370cca47ba4
+size 1270648328

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a731baa1370864ad61cf8fe8000cb8e1e266529206824a3ce96b5229eb3c53c8
+size 1270648328

model-00045-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a636f872a931396d2fdc57b6c715294e14b3c8040420ffce856a2a0a18194916
+size 1270648328

model-00046-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5365e31c27cd13e330a7135f7251f3bf16e99c8504acffa9e8190b585eb773
+size 1270648328

model-00047-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcc5d06065d2a564894657945ccfe9411762421c2c60acf91de31050cd4d84d
+size 2539429936

model-00048-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fff90a30ca808d86dc24f9e3eda119832ab69fb1f88ae4cccfbf0e5ee409a1
+size 1287438264

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
+size 20217442