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-4.5
+tags:
+- mlx
+---
+
+# sjug/GLM-4.5-MLX-9bit
+
+This model [sjug/GLM-4.5-MLX-9bit](https://huggingface.co/sjug/GLM-4.5-MLX-9bit) was
+converted to MLX format from [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-4.5)
+using mlx-lm version **0.26.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("sjug/GLM-4.5-MLX-9bit")
+
+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 +1,51 @@
+{
+    "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": 131072,
+    "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": 32,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 8
+    },
+    "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 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.0"
+}

model-00001-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9fddc82c31d007499c4755eed47928619703699fd53fe4bb41db4b3affc8d0
+size 4954712391

model-00003-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e838427be1bb6af81b9dfb07e0ca599b85d4b7949720e8b139fa0d1b9a4e094
+size 4428322532

model-00004-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91bf3c5bedc836b13ec4207cf5eb74f3eea6091a8ff44d8c1b8a4555492c1bd
+size 4428322548

model-00005-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc0fd6ffd1a3ef4ac850207708d21a48f6f3fc3c3448dc707fb2fb3f1e3b97d
+size 4428322540

model-00009-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edef8ea0fa869900e1b2dcd565021c635a807497f53390ab6ad14764d71b2cd
+size 4428322587

model-00011-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1111972ac5dbbb46e0cb9086400e18d4b0bd58de9df3829ac004b0d72a3f18d
+size 4428322555

model-00012-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e4efe03b6f456135c6314ffe3da9c1403052d6d058c5c6374f7a073c3651f7
+size 4428322567

model-00017-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33cf073ca14a01827ea33eea7ed868285eff819dec12f1ad9fb1cb57a4ce0d46
+size 4428322583

model-00019-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ebe675c1cdac9e21116056ee1219ff01d0269a23164c1887e2e1b6c2f4349f
+size 4428322583

model-00021-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333b37d0b190720ef41be7a35a86cf5ee637c11b4a0f11295176b304e1053f09
+size 4428322583

model-00024-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7d9dc05e17d7efdae1f734f6ceaadf87366f853df827445abf5fddaaa06a84
+size 4428322567

model-00025-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edda667ef0e139c312553f5b4cfaeecc30630cd32ab0f18400f31817e03aabf7
+size 4428322583

model-00031-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc9bb74da1bd05055ce1b892336d4a60a85e039310c1e0ad13b763ac6eabfcf
+size 4428322577

model-00032-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3f8dedb731d9c1d112699ff6af7e87715a8c80de7d6d7adc2bd9218f90af43
+size 4428322577

model-00033-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32adac83ea8bfe2140346d0bbd49474b721f66961b0e6520753f61f6a3725d30
+size 4428322583

model-00034-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef96b4fbf6ee9e129e5002ca8258dce4fd93b7215becf66614dc1b55fa5db11e
+size 4428322569

model-00036-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afa32e6b637c808888a380a94fcc6e2f245c70358e872377fb32ce2daff8109
+size 4428322581

model-00037-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943f697e0325a953358c642ccb7bef68b03f4f08a1b333160289f87e4e245fd0
+size 4428322531

model-00038-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293266e2e07c27d67ddf8b4c57e0c3b5b685b246b6557ecb9647ed8af5599179
+size 4428322583

model-00039-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba2009504e0fd6695600de6453d699854772bf3c56bf5680f5c4a2a7add2069
+size 4428322583

model-00040-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818c03a384057c4257e9ae85ab2973c8de621a4d387fbbcdd4609c2f1571d77b
+size 4428322583

model-00041-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576a215e5b87482b97efafb00e446559bbec00fc5586d3a3b58271597aff1115
+size 4428322551

model-00044-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b324460965fc140f7ab6d99a161a9fddcd353cb5f3c3d3033484d267de7c48d3
+size 4428322587

model-00045-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f70a410ff7314920e7eb713c47c00638cdebaaf90bb19b2b59baceef2040d1
+size 4428322561

model-00048-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c48a15999b5d2a98fd001a527cee3a5be87543e423b7f5dc686edd623961092
+size 4428322579

model-00052-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa2c21e97ba79bebbd79dcf026dca0517617f596541d6e447af181d4716c846
+size 4428322583

model-00053-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11450d28b7e6244070435b0c890a9b2094adfe9c5b3d6a6b700f2c3831863aad
+size 4428322545

model-00056-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6fde9243cc664fd731b3dfe4bc5725bde3e8ae58b8380449d47b68ff423357
+size 4428322583

model-00057-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7638c5d9653e755d3280ca7c9ab5675b4685eacd7afb609d2861dea216bd4fb7
+size 4428322583

model-00058-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cbfa05f47a516b120a187a723d2fac4b38870334dcc70441aa9ffe68e57741
+size 4428322579

model-00059-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d325daba917f7dc8235ce2e1d198bd82aaff29c2483103b73af5531f91e0cc
+size 4428322581

model-00064-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d488ef9d957dcc24794feddedd4cc78e509f4b994e21532bf7480dd2b626ea
+size 4428322581

model-00065-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64ed9b3b6106a123fe6373c8c2d275d6b5a3cbc60ed6eb801bc031580edb280
+size 4428322587

model-00070-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f33277cb89be8a7c7d66e5f1276c0692ec44e93a3b2e8d79547885bbbf6b1a
+size 4428322587

model-00072-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a28a1de376e52de4f49e02581f5ec3ca1552f3ecac1465b67b50437c4c223a8
+size 4428322583

model-00073-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4554c9cbe657c9267aff1a60e6354f5ec0bd925cd5688f4c4235291fb0244fb5
+size 4428322587

model-00078-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dc65abdd9fab0621b99ced713d88c2d95bd1ded8c18dd4f4943d2d85f89d17
+size 4428322587

model-00079-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339a275d0f0e89bf090ce804318b398f4b4f7b7fcf8c54348c73ef5126d71ca3
+size 4428322579

model-00080-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f854cafc4c10fa98a2e7fc09c5461fea643d92355627df7069acd9455cdec9b5
+size 4428322579

model-00081-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a1c55a363dad7a056b6d365e2e430521a123ea1e71385158435cdaf6ddbf94
+size 4428322583

model-00084-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464adc444b7319ccf8d5247bf00929bb7ede84047aeb88a1e89d160bdeea103b
+size 4428322579

model-00085-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66aaab6c49a68c629411d9c517b50536ce75ee0cb12489d5bc56a65ef3ff5336
+size 4428322561

model-00089-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22903eb0c121ea6d1cd5f25368eb8627514256ed91ea1859c43d1d851bdad41
+size 4428322569

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