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

README.md

@@ -0,0 +1,39 @@
+---
+language:
+- en
+- zh
+library_name: mlx
+license: mit
+pipeline_tag: text-generation
+tags:
+- mlx
+base_model: zai-org/GLM-5.1
+---
+
+# catalystsec/GLM-5.1-4bit
+
+This model [catalystsec/GLM-5.1-4bit](https://huggingface.co/catalystsec/GLM-5.1-4bit) was
+converted to MLX format from [zai-org/GLM-5.1](https://huggingface.co/zai-org/GLM-5.1)
+using mlx-lm version **0.31.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("catalystsec/GLM-5.1-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

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 +1,69 @@
+{
+    "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,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "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,
+    "model_type": "glm_moe_dsa",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "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,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "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-00003-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79099169ceacbb845091a31ce7c5be43be4d45cbb8db9fcc39e0583320aec15
+size 3947717330

model-00006-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed74077c6af97a484a61dedf0616f2310738e62ea8530e52f19d34bbfb36e85
+size 5335155728

model-00009-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0eb85e4927348720709e5f7a4d934cbac7d75012dd16538a613621fb0f6afc
+size 3947717362

model-00010-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad50882d0ace08f77c4086291c095c2a7b0643e45525e5c95b1fba45c6ef3015
+size 5357003398

model-00011-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4655079c79dee65cc05f8d35bafe8bbb7f7b94fa26a2ae4d11f56a427c6d7f4c
+size 3947717358

model-00012-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1748c370ef34c1cf89571bfaf2f3af7d13c0c87bcea170917ddbdf120b7b54b
+size 5335155736

model-00014-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9cfa97eb01846afac0d2974b95b0e23dc6beee6d150b890d10c8837c56c7fc8
+size 5357003402

model-00015-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a1728be9b6b7ebac95bae34850c24f8eff85e774d29c4f9c1978804edac286
+size 3947717380

model-00020-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dc6e5b6dd98a86699648fa43d4d9d6cc7d6eba7c974f42ec792b47bfe02c49
+size 5357003394

model-00022-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724537dc4971c8e04927caf6f4b3ff9c93e489cac8217574e63e1385acfc9514
+size 5357003398

model-00023-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6752d168ef6dbe5ae8b6aba82bc18c214e4115dfdcb252cacddcbbb5a88ca864
+size 3947717338

model-00025-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4eabed2d32d3abab15e1cbc312b96328391a1eb74a66b23d6153619da7a841
+size 3847053950

model-00026-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9689b3cc2ca5c2d7854bfd41a088ef143a4576bb84634a2dcf8377ca72a355d4
+size 5357003402

model-00027-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6195d8b43945b7bc6bf311acc41f8b5ead7d313ff66088601e913c4bc43083a4
+size 3947717384

model-00028-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9180004097c2508fd8a91a0da68045469fc5f6f96e56aa42d4d435bc3ee376
+size 5357003398

model-00029-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4182cbb09c494d74bc045f000eb094bfc88eb78bb5ac23b644f25eaa5ab75e94
+size 3947717260

model-00031-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e316e7e2e360501bed7af89abd2bc1d38522d0bf2aa1a399f8f607e01f280a4a
+size 3847053956

model-00034-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f20a9ee594a13ef549d83057aa53c7296009b4d89c1708b3de11b101ca89e51
+size 5357003398

model-00038-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8a980afc55899182ddc33dd40060f532fc39bb2043186e98c7f29515d2cbc8
+size 5357003400

model-00041-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08691dc51962f2d806be37e19b3549f1885206e7a87a5ae13c44940a78b4fd4e
+size 3947717182

model-00042-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f337bb03a1f510b78d214ff91cf742af6db9bda80c6bcea44adc9e55cfbbc7e
+size 5335155738

model-00047-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677ccc4ba65b17648732af64174525eedef343aa50dd27f1e7ed9516b15612f5
+size 3947717206

model-00048-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb320895a964353722432ff36a47f8ba9d5ef24f2183d2215e64c6328454428
+size 5335155736

model-00050-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffd6a5430cfdcd63205facb17acc710d491151595dc3e67b54780c0cf69ba26
+size 5357003402

model-00051-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169c7dea6e4db05cbe4f8d821edfba36e1dea48ed7878ab148c4adb56aa40e2e
+size 3947717380

model-00053-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073766ec18761334f5bfec190f0727e2bf289ca7100c50210b29733100ea85de
+size 3947717308

model-00054-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857def919a5f9b78203469c2b72be9e56fc07f05c71dbd0aa356158b08a60aa8
+size 5335155738

model-00055-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bad2bc81a73b14184b240252d9e4bcce4b6692547a1adc8024d3441d0f5c311
+size 3847053918

model-00061-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fee6c50228c3b690d89d5dfd043849c575856aeaf3155cdff6426588025f90
+size 3847053956

model-00062-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db48505e0c38aac1a6121ac6722d93db4937e525b34ff688835f227485845b53
+size 5357003388

model-00063-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9b5a2383a037a85fff72bb619b4012773f9e18127bd16a32f7baf32d00598d
+size 3947717356

model-00066-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4a4aa2f51d29c06bf1cf85c1f84a53372a4ae75f2f23329681001bc39ac442
+size 5335155734

model-00067-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efc115600b3d9ba770c8d8e3445acdc9d3ef32988b1a0e0e3066856e0294cee
+size 3847053928

model-00068-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772db26190b6f876bb6becf268f1f52d3333ddaa4043f72dffbd8ac53c10090e
+size 5357003402

model-00069-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cd01c84c5841b69cfcdffe816a5ca0a62d5b9c28afc8796f10d46139ba9524
+size 3947717300

model-00070-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d57bb63e3a6a43b3bd44ce1c1c9813f4955e3e19bc312d17d1a56a4f942c5d
+size 5357003398

model-00073-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b223acb29bbf70320df36d588ca3ce782142ecaba848a2976a1e18fd80598aa8
+size 3847053950

model-00075-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802476b9c73a79f7b4f0e02e3123c114a851de9319b9276db1919ce4c662ca26
+size 3947717358

model-00083-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f916e6cf6582bd059b37c319792cf4197c56d95009ab775ffd75cb288d5d61
+size 3947717200

model-00086-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9fd527cf28fc0cdd57c9771acc817f3910fbf2b6c8be4e3354517a7a0072be
+size 5357003402

model-00089-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69afc20b3d872474e471187e558c086db797aa688f90b7ef6141b3e6c357c6b7
+size 3947717258

model-00090-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea48c7ff47af4d152c5737f653563f0db1f4e96bd08aba1d02eddb99fcfd528b
+size 5335155736

model-00091-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a9a2a609eff3fbb05e40be6cea16de70caeb2dfb122e04896281c73b66cb17
+size 660347957

tokenizer.json

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