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-4.7
+tags:
+- mlx
+---
+
+# FramedStone/GLM-4.7-Q4
+
+This model [FramedStone/GLM-4.7-Q4](https://huggingface.co/FramedStone/GLM-4.7-Q4) was
+converted to MLX format from [zai-org/GLM-4.7](https://huggingface.co/zai-org/GLM-4.7)
+using mlx-lm version **0.30.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("FramedStone/GLM-4.7-Q4")
+
+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 +1,53 @@
+{
+    "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": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "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-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed97147143381f41e1fb4e7cf7da8e713011c32dcea7fca4fb034dbd9bf94a2
+size 5360926816

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2807d8ee7d1bef4d63be47dc555d6523a8394f4cafd3c6e5a20ac3feedec3f51
+size 5268767075

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726319ba210242c814d47b3044846e79bccad8158217c0bb4fffb7ddb4757909
+size 5137804969

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b11becf9038976a9e2108f16902ce8a370f560bd2cb105b291fcb042f23a284
+size 5229445422

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756df9248be2e9995cdda46ee9cc37fcfcf73ac202c7e970ecb3b3e3b2bdb931
+size 5137804982

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2509e4efe4805359b7ed8b4e992441e94ce67db931dfbe0de9644405fd27ad61
+size 5137805042

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231d1ef883861b4089282ab1abcbef002f98f6680276f892cab648f9e733f63c
+size 5229445386

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7128bce3d04fba09531d5823816ad115adb5c9efe0c126bd94724b694003ef
+size 5137805058

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b505089df494e95fcf7ab1b1a06a85b42b8a144f6bdbf1a5fe1f2e0da7bb83
+size 5137805050

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8c45e122d066103bccbc8ab1ae3aa083b9cbacdb9339c12484bbedf8bbb5b5
+size 5229445426

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043ea77203a2ca7c52a6f1f85b458efffaf34d4c5516c446c9918da491458697
+size 5137804994

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbff1e1d70f01fd29f6589ce336073d7245300c9e903350d18d9b053056dfac
+size 5137805088

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192fae7edde9650e805a741c0dd62933c8be24ed42350618a086b125a2a04cfb
+size 5229445408

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668640ad51b8b98e724a9dd2491518ecb3f62fc24e4c408edce61d3ebeab7b77
+size 5137805058

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec9d33233813dde368d000cab1ddb13494770b0f93c066c5f9672c03ac05bab
+size 5137805046

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae759cf440df10c57e07ee34e8fe4a7dd791d0ccc05207ad480c4f204b08483
+size 5229445388

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e0d4cd25d2b7cf46447d8689ea7266b18f02e5e5645293f00690d4cb7bba76
+size 5137805020

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7227c30ae3b20a4525f8d28f8412b1fef19706888bcc3af7f59a79566006409c
+size 5137805050

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf02e8a22178ef1a5c71fca8ad87871906980d5774cb469fafdcedfa008206f
+size 5229445386

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085f15c8e10e04b422eeeece6ddbb1c7d7bed584cd67724937265eba8e31a873
+size 5137805054

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4be4c7c8b5f10d6b569c415ca3ca0471f77aa3e74de342c791bac3b2b3db4c
+size 5137805018

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8004d39c72432be07f342a508dd2a337974eaf2b7f32397d8b8d05ad6f3bd656
+size 5229445342

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23c379b5b5c70d25194b3378897bbac6640174c55cd02c0ab48e04f4e781d2a
+size 5137805062

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6695cde4282503117cee8da906200f4f7e6569167532eae86f56ff717986dd
+size 5137805094

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677783266a665d04fd244b888b044b3c29e11aa431cc9cee7dab712a9c68cd4a
+size 5229445330

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe93b91bafc1eafe78f8736c1fbcb73d6f0f024a04ff457be37f25ba7da9ea39
+size 5137805026

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e269e0c99bc3dbb2d310f5b1ad07bdf7976322fc2d3eb2ba452a954ea03c8c6
+size 5137805032

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0e43f92dc7582d501d4903acfa722cee7feebeb4272d12f0cf9504ebac000e
+size 5229445402

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a71a5a636fb41bd42b8544ed8d8e77624caf6d5b4130ab25eea936fb4efb96
+size 5137805022

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6d46b4221cdc7bc8b466fc31476b2c2912319e8f8e714170f7c058d686add3
+size 5137805092

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9be713aed4e158b9cefbbf065f7fc95650732f421e8c0695fe0e695af5564b2
+size 5229445418

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391e888f16b530f21ee4c9b82734233524269011ee3762de927e2fb5118cf772
+size 5137805034

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee734726dec4c7666ab7d5326c3ac36354cc33fd3c638ea0641ea32d570a5281
+size 5137805040

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d0c37ad2c7a704aab96751050fc087e1baed2b84a9a1e3dea9961ae8219bff
+size 5229445420

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c195f3347a3da806161b87c135e7d537edb417f6186dda4dbeca0f59a6d87454
+size 5137805066

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1b700fabbf2ee748bd6cad55033b961f066ca8a625a38ac07484800081412c
+size 5137805092

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d013d131f4724b6531e67c0917333a7412f4e285e643bed9551509741a540be9
+size 5229445412

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ef883e1d485460a249a88b6b079bce43635859062cacfc39cde01eb8c567c6
+size 5137805056

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58695d499b47924407fdb563ad61f62d016e87d2669179a235785c5133abba2
+size 1866990874

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ccf2252fe9cd23ada23a829ec409aab397dbd2ac4f372d3a1a23d1f7c72d6b
+size 19970686

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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"
+  ],
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_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"
+  ],
+  "is_local": true,
+  "model_max_length": 128000,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "glm47"
+}