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
+---
+
+# mlx-community/GLM-5-4bit
+
+This model [mlx-community/GLM-5-4bit](https://huggingface.co/mlx-community/GLM-5-4bit) was
+converted to MLX format from [zai-org/GLM-5](https://huggingface.co/zai-org/GLM-5)
+using mlx-lm version **0.30.7**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/GLM-5-4bit")
+
+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 +1,86 @@
+[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 +1,69 @@
+{
+    "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": "5.0.2.dev0",
+    "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": "5.0.2.dev0"
+}

model-00003-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55c45ab728c2df37e29b224ca4b6be3892a06333bc15eb36986da18d2141ab2
+size 3947717330

model-00006-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3776116d2028d3fa2e117817dfda73d8e712e1cf3f6a53b508a6bc76fdeedcd0
+size 5335155728

model-00009-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1fc6ef3ebe2b78258df5756bc297c521dc177e70b7a85af2838908ba1cdf3f
+size 3947717362

model-00010-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18b7dc96903545754ac99a9ee6daf3904f2ba36c0dbacbf3204be804e408662
+size 5357003398

model-00011-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936c350081f4c836782d37e6c6cac1442d058a4a4c7d16f43c13d76a4644cf6a
+size 3947717358

model-00012-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8936f1cc1e0397f9fdbd5bede886019820b275aab7db10b4a7f1f1e3de6945e4
+size 5335155736

model-00014-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df851ee107e59e8480c957256868fd706cd684f7ac19fd39e57bd1662a22718
+size 5357003402

model-00015-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a359215a77ae3a4609a737271ad7ce3190f45a8de034cb5b4757b2e1ab331d9
+size 3947717380

model-00017-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1089db8e0a259ae289aa491d1c8f67750d3afb2929e77279728054051ee68fc
+size 3947717212

model-00020-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa7b0c2214d4a257fa077d23ba839bb37778c3ff8df321f3046c370655454df
+size 5357003394

model-00023-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883a7a2c1949d29b6f9a99acc6633beb3b690b29e59d0f996e6281a336e30fdc
+size 3947717338

model-00025-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a2ff1aa7170e8e4623d833b19c1824caf584829448546fb5fdec22ecb6876c
+size 3847053950

model-00026-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b34d890d599d0584f3ba7af8cd7a37fd1f4198560b434f2109761181631cc7
+size 5357003402

model-00027-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22831893475d906001f8a6590dce2e6bfa07d5bf859a54c5319fad9a0b5329f1
+size 3947717384

model-00028-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9395756aea64958f2560f2ef88d1f5d7ed81217f2f7b6e66a9f5d7b382a9e128
+size 5357003398

model-00029-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5cccfb21344335cfa5d48a106ece94b4b73e319a14a7a457eccf125ffbceedf
+size 3947717260

model-00031-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a2a72031aa99128ae31064595c9cc79d8b78b8e1c8227d60b2ac78d318b869
+size 3847053956

model-00032-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f004db6da20a37967215070885af018131fd9ea983b73de181b47929ca36c187
+size 5357003402

model-00034-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80e4e24d30f8ebdc6dbe1af0f2f6f804031b2998a411c59e201fcf0e022b5f2
+size 5357003398

model-00038-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18872e40dc6c1e106530bbb7aad77f3d1a3c1d3a01eb8dfeba23d59174419783
+size 5357003400

model-00041-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651ac755d7ffc36bc70856f9cfc37eb43a52344735523c71861959c64751373e
+size 3947717182

model-00042-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda63172e00ade852e858109807ce20e6b836554217347bf2ed839430a72729e
+size 5335155738

model-00047-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbd7523e35bfac87004db629f293e8ef1802d91589f2a0ba98eca3e9cbf15a1
+size 3947717206

model-00048-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c7ba175da56606cbfd4fe33fa7ad9565455582700dd7a815626ec5a465453b
+size 5335155736

model-00050-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12cc3d368b1e8119fbde2464eb4e719405b98fa2fc82ef547cef3b83f6fadbe9
+size 5357003402

model-00051-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35d0c685d734f8de676699663498fb7c978d591ff5b18e6dac814869f3620be
+size 3947717380

model-00054-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847442e71b2a275cffbff518ae385a068b7bab71e819e2087d4ff2b6327d8e2d
+size 5335155738

model-00055-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8baa28d54d8dd1d840055bfcbe31c083b65c1d8db15e95304ccd12de5de36e
+size 3847053918

model-00059-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0698314dfdb74f4d23dc0a0a330ced642d28817ca9c545b0a900d1f725a8656
+size 3947717312

model-00061-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e4546d206bedbd88ed4e853d9b11ccc08dc286b578ec644ab9528fa8f59d13
+size 3847053956

model-00062-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dd9f48ef1aea85f688696058396cea05a50406e0650145cba56edfeab931c6
+size 5357003388

model-00063-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8a1b4da64015451006b963ea2885875e4cca23243d599ad6e146dd94316174
+size 3947717356

model-00066-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635e986fdb0e4d494b6ec4e4518f55e900145243d5d15a57c51790d420838178
+size 5335155734

model-00067-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fc25ba10d0ee929ece8057831918327c47acc8246f7711752da04702fea927
+size 3847053928

model-00068-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9135d8e84d7990a8004e439f1ae5bec031f5ec50c2cd6cf1f81bd4ce4daa4904
+size 5357003402

model-00069-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d7dbd508806905b224cbcf5d00ee6a329676c92c38822e38cca045faf9959b
+size 3947717300

model-00070-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4316b86d40a45eecf9719eb53cce515fc7b9da579d7b85519f6bc9ef4debc1c8
+size 5357003398

model-00075-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b42e970ff93c1ef3f768c2640c69fd454d37ae08e1f186e074edab37c5e961
+size 3947717358

model-00080-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a5128f9c32fa572d1ad93aa5dceb81a9a66e6276bfdadff38e07e3cfedcfa0
+size 5357003400

model-00083-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0a9e9e3733b8938cf232e25154cfe8ae16de446756df41750a0873606d0770
+size 3947717200

model-00086-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fded92bfa1c5b0b2709ed49c6406a88e9508217b8437edcad24b01077ff68d0e
+size 5357003402

model-00089-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542a764f9b91514fe67074aa197a42c1185193a5ee6760cd1df3ec6d43a6529d
+size 3947717258

model-00091-of-00091.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05b3469f93f0ec9d4341052fa58e45c1c7ecf55f34f712cfa8cb276356b5090
+size 660347957

tokenizer.json

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