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
+base_model: zai-org/GLM-4.6
+tags:
+- mlx
+---
+
+# mlx-community/GLM-4.6-5bit
+
+This model [mlx-community/GLM-4.6-5bit](https://huggingface.co/mlx-community/GLM-4.6-5bit) was
+converted to MLX format from [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6)
+using mlx-lm version **0.28.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/GLM-4.6-5bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,103 @@
+[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) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- 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 loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<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 %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</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|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,53 @@
+{
+    "architectures": [
+        "Glm4MoeForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "eos_token_id": [
+        151329,
+        151336,
+        151338
+    ],
+    "first_k_dense_replace": 3,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 202752,
+    "model_type": "glm4_moe",
+    "moe_intermediate_size": 1536,
+    "n_group": 1,
+    "n_routed_experts": 160,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 96,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 92,
+    "num_key_value_heads": 8,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "quantization": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "routed_scaling_factor": 2.5,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.54.0",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "temperature": 1.0,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9363e7f08f7be39c8650f75bda19bdd01fd35cf9cde6a8ebffb2abcfaed26766
+size 4869733950

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432b7ed14a1d96b1bfeeda42aa72862569b1c233e30a0a00f4f4ddf5a5d6e380
+size 5335067714

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57b34127202b5013e68dd20cceb01b548ceb41443dc7589581c0aba8d945232
+size 4627279021

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0c36f3f9a40297397898f425ea5a94bcdc6d64204b10e2f70da37d53884983
+size 5366825498

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347fb923b1a2701e2672bb2b5f7c85f0dc402862ab3f8fbb0a29e0d2f990f2ae
+size 5356508322

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f935bf924ca026141aefcbe90edbae00ef1d5f3b4eb07e9216a86be49568aa
+size 4587957422

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939d1244124e9cb353caa413e751b694ef94a3d08678fcb6e2f595391fd9c68d
+size 5335067884

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b648bec0ba0d8b84db70c89cfe03ec8745aef17d97c79b6320b323c85f6c4d0
+size 4627279126

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ba23f5e6ec40b921e801574d705fd0f9247cfcbd1f9cb6bbbf61e5a9042784
+size 5335067832

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff85a3105ef4e270ca38b33dce38bfc87ebd84e8ebb90125c94c8d5355d1e3a
+size 4627279106

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e76fc843f848b1fc699f2c2b6dd0a74799cc1dec9f78af0abfa394a6252c0d
+size 5366849422

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0f4aa74afd073089333eb9958df8b60f13f30faa941caac9c6e7aad0c447e7
+size 5356508318

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7f0dd8bd2c121bdf3525e41bdaf1f40a65965313a6de31a38a7218d75b1b57
+size 4587957472

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d70eb1d14f1d61beed5dc80cb4dc471e486f4629ce11e9e8296f60abc81834
+size 5335067884

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba1dff78331df7f0152e2c53de574f62a93bce128693fcfc075a654c849b021
+size 4627279118

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b0db9d8b634e12f17245f1ca7e89cb337bf7d61670fc724cdc30bf11634a7d
+size 5335067812

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cc7daa339c9610c25cbb4de4e8f43eb8d4f9bfa86d39f8270bb779d9b93fb4
+size 4627279108

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48d6496366ea8a7b74f5223b38c1648a4f33a5d77d3778c8f8ecaa933be5a50
+size 5366849440

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce654641f663f8189c60cbe94d44a17fccfc86764ce964b2a311ab5f2bb90c1a
+size 5366825488

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e6b1e49bc9c3f5d02bb8421b0acc78eef5c72d3cd81dc49d6e00ad0b52e2b1
+size 5356508318

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd11318112f2c846a89a507e70b3fb17b18e2d76ea2f2f2be6e0d7501cb50ce6
+size 4587957446

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcac2a3f785f18841f0756f4845b09a2ee9e96b428e0d5ce0947546bb44d486a
+size 5335067812

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22070498f7085dc64b8f93268add128c8837201857ee327564d79c973e122a9
+size 4627279162

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a4c843682f926624a98bd4a0c4c5cec002425a75e7518418102e3dc7d298f5
+size 5335067730

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c77fd875f58d8684aa9b1f72c99506010b57974d980be84207e10f176f280d6
+size 4627279088

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6484e57343a82d4dceb34d55357131c480bfd48cddb175612fb8b95ad81724
+size 5366849436

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71d0ecdb93c35aae878d418d65ff8ba7c5e72f31c11b1853beb2c7a3e8239b7
+size 5366825484

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51147d63f41159f9a13c63b1c7666e6d8981c51b706e4f9baedc42eeb6e07de5
+size 5356508316

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befe5414506553c369c972652144c60bacd33a80ecc68b6b01cef7b26a406387
+size 4587957418

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c1b949da8a3eda7d3933ac38edf6de547d8edc6880da82c3c7aa191e2dedc0
+size 5335067776

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55073bb13f8c054e709cf9ef9b80e9e2d1a16b2123b4568672947fb13cdf8733
+size 5335067844

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60c8d69408591b21380f710d9efae941a6482cfb76f793081194a32379a43ec
+size 4627279140

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fca5dba170eeb5340068e9dab45ff601d7bddeb942df13cac8e4dbdd2ab1219
+size 5366825514

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be23c675ca3ff36a5edd65550d254431584855276148a47679b09c80a03504b6
+size 5356508280

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a331734f2d59f82956aad835670f51876a0204c27fc4a8e738b7b22c8ca5dd9b
+size 4587957432

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539522ed03d86e48b1b7c19e9bfb7209d5e306144e05c0bdb3017b093e955f40
+size 4627279148

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4a092e1e32f404702707c74a469d80a4b17239ec1b1e161197d12af7de4b7e
+size 5335067846

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb566a99a836f4260ca06c20cdd03022b3d1df27f1eec807e18ec0223505c347
+size 4627279102

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2205bbf35cce9cf7c4243ebffe092bf3e4b18059e2c15430fe609a5e02e4ffc3
+size 5366849432

model-00046-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d8cca522e8272f25197f4973b400c632bda3c8713ca46a2954fc2062a4f3d1
+size 5356508314

model-00047-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a615d62022addd8c3e8d7408b352bf20c9bf234c9431286b6263223f716acba
+size 4587957478

model-00048-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4758996822e5ac7f0ccd22e79b9df8517f4a7e6094ee4388ae87cb40b236855f
+size 4123286164

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
+size 19970700