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 +1,117 @@
+[gMASK]<sop>
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+<|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 %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% 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, thinking_indices='') -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- elif m.role == 'assistant' %}
+        {%- if m.reasoning_content is string %}
+            {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%}
+        {%- endif %}
+    {%- endif %}
+{%- 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 -%}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %}
+    {%- set reasoning_content = '' %}
+{%- elif loop.index0 < ns.last_user_index and ns.has_thinking %}
+    {%- set reasoning_content = '' %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</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 loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+{%- endif %}
+{%- if m.content is string -%}
+    {{- '<tool_response>' + m.content + '</tool_response>' -}}
+{%- else -%}
+    {{- '<tool_response><tools>\n' -}}
+    {% for tr in m.content %}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{% 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 +1,59 @@
+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "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,
+  "index_topk": 2048,
+  "indexer_rope_interleave": true,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "model_type": "glm_moe_dsa",
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.4.0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.4.0"
+}

model-00001-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e488bff5a538ff633d02a4841f29e20d9944f7aeab0100429b610baa10ef3aab
+size 5342821416

model-00002-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0d8c9df21ced607a57835c7f7e5675488f5b9e56c3c889b75903608dd336c4
+size 5351970840

model-00003-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbef1bf958040cb5140dbffcd5316bf7603e3b233a93607c12830ae46c130813
+size 5360347320

model-00004-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b8eb673336fc0fdd98d9ac77a4795d1b153311cd7fc993ca231e5a52773e83
+size 5360347208

model-00005-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8548f35ef0004fea726c55427a46cf819949fa548e99123637d2c6643e196550
+size 5359985352

model-00006-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed50a7b1a1c630e87ed7b959243f290d78f01471e3fa7591a7e52017a4b8131e
+size 5360347320

model-00007-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84b6d1726a4fa595ecf43d8e1e9c2607284410d38cc1e2ab03e0db74d590b29
+size 5360347320

model-00008-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92843c468579fa94144261e53bf0dc1546b478f51d487c32daf8b113928edb0e
+size 5360347144

model-00009-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ba244428406d32f81941b8590bb8bb1229a0a0d19b311264e5541215665692
+size 5359985416

model-00010-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498da279e81ad52c6677d317b0b1fd9aa550576add45685914a63293f53c49ba
+size 5360347312

model-00011-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72086dc6918843ab021de07da5ebd056e65260593d112606797e2f07b4c9779a
+size 5360347288

model-00012-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1638d0a170f10f3c37e10bd67e6add9a56eab2fccbcfe3022bc7b16e1836437
+size 5363494088

model-00013-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea140692571f780911ee01e77597e35c2945cecad0967c3b8bd763ae5cd0c72e
+size 5356838488

model-00014-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0a0b85220007b1ad4ccee9b8f7a7a651b69daa3bb610acf5060a2336530418
+size 5360347312

model-00015-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2521c91a4abc071a32c34b0143c9cd4985c9927c34f80f06c6be4f966f2cd3fc
+size 5360347224

model-00016-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141d7045238dbc7de2a9a62ccc9851b241acf13c028198728f8304d1ee4cf4cf
+size 5359985336

model-00018-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5dc547cbbea4ef9e07e025e4ca939d05d9adbbe5da764c1f2341e2a09dae62
+size 5360347312

model-00021-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2ea4190e8f27cc696d2c13e6669a3d41b619963787b5aa8dd4301c4ba2a967
+size 5360347320

model-00257-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0a57854e9a0571c6d056133526bae1cd4be9ee5b258ed4d1f0fecba72b5686
+size 5360347320

model-00258-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24664ae866c9194ecce39272107a452821500dfcc9346aad8b1df85e310596e3
+size 5360347320

model-00259-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01b806453d7ed3671aba421041f147381f9a3610739acfb3165734ef9b66da9
+size 5360347112

model-00260-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb5f22090302d9ebc5931f1ba8eac105159c8f0e94a6dda0b1ab67f64b127b4
+size 5359985440

model-00261-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda8875d06dce2bc2ef67fa0a940ec5114dd83d7aa4257528c586b7fc51b87d6
+size 5360347312

model-00262-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6ea5530ef3c56eff3ef84d0f45e7e34abab551f44fbd747516d10aec23d024
+size 5360347256

model-00263-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b3de596edc0efbb0e94cb1b5a6862ec7d4f054f90b935af4d2a58664f07973
+size 5359985304

model-00264-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b5f5f1ebf720e88af3accd1812f8f392e1c80f958c605579044a0b51bfd4f7
+size 5360347320

model-00265-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1d5fe7224b1e801cd0f82f636b332734537eb697cb8a8e74bb06825c5674b5
+size 5360347312

model-00266-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d449faa20681471c90f737ef6264ea266f3541ab5a3b2db8f927da7ee4fd44cf
+size 5360347192

model-00267-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c491d67d4cdf877677c2186d8baf5ec631994956742bd4ebbceb0f51cad16e20
+size 5359985368

model-00268-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6666e5f11c3c3ed1ed4e74ee40b440e69033c505a3a9acb53b97139e35b7e7
+size 5360347320

model-00269-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1239c41ee244d42a0e05d51281ac57a9b29d3887dbd54fc4701de2932a4237fe
+size 5360347312

model-00270-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a18fe6406132d00711683d270d3dd8d669410ea3264b64a742058e23e2ecb1
+size 5360347120

model-00271-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f31356362ff509a560a9efac28e2db141c4c7786ab095fff96a022599532e9b
+size 5360009568

model-00272-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53286eb550aa4a1ec25844f5a4debc164ce7440807329a17b7c77c883d5d5a6c
+size 5360347320

model-00273-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5b3961d481a55c8abd10c7f3a2cc4c510a778dee0e7ef1d045971a724c6ee8
+size 5360347272

model-00274-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555b082c0c6048fd308fba60473d608701485cd3ec33a7b41186fbcdb7a9ce87
+size 5359997696

model-00275-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2401fde388be2f9859a53c7dc9115ee746b60a9ee2064260264a6c918403703e
+size 5360347096

model-00276-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17de955b9f24b39ef1b1c7c14479aacdb6ca7cdc2f5220eda747e3a6552aeba
+size 5360347104

model-00277-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5063da153f330988acddf67563ab5b12b79d77b79b5d18ba0585770080dc8652
+size 5360346992

model-00278-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a7b33f1df61a68b4352c54abae0186c7e05606a5589524586e1e8c5db4106b
+size 5359985144

model-00279-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d428386f877c6f4581ec06b72af3efc671c1ea2658e389703f01958d68e3542b
+size 5360347104

model-00280-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7702fa6ba3b0f2cc88738c09d67d02be757367114798351338bb09a9c203fae
+size 5360347104

model-00281-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a7d344fb942cc260dd5417a1891f7bcf28a0fe7d6c9366b6cff162e9f74edc
+size 5360346928

model-00282-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608f9fa0601d99a3e911103bc92700df6183f70dcf7b7558a85d94cc81685aba
+size 1962582048

tokenizer.json

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