Add files using upload-large-folder tool

README.md

@@ -0,0 +1,31 @@
+---
+language: en
+tags:
+- mlx
+library_name: mlx
+pipeline_tag: text-generation
+---
+
+# mlx-community/GLM-5.1
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/GLM-5.1")
+
+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 +1,59 @@
+{
+    "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,
+    "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-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4729c89a6b5e56e6cd307c644765df45d6cf0afe0185059d1abc88585f0f9bb5
+size 6442451103

model-00006-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff06dcc02b53bfafd3876f6fe9ffd7168a81f18212dbd002d2bcef19ee43a973
+size 6442451105

model-00007-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae246c0759e33a84cb7c6ddb4854581d293b0f6b2c2c429087fcee69967544d4
+size 6442451103

model-00009-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b30e555f2a5b250a7f95feb133597012d940753731f08929cdcd680826c9eea
+size 427459421

model-00031-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34816426cd7a45a722758195f28575468cdbb46e95760d986c65c32d9bbfe155
+size 6442451104

model-00034-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7820a7d2988603f1e0c64442f194e4602f8bb23db0db3174a7ee7d76e02d2cc9
+size 6442451106

model-00043-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c19f45153396b905935ff36320b7eaa79c13a48a0cb719fd9cde0aacd34e9b9
+size 6442451104

model-00047-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900313aa57922d9e7e8bb25a30d36a1ca57aff601e1008dc9c4cc1a5c4ca8c57
+size 6442451104

model-00048-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc534a7e4e1d72e93b83567ec0d6fd460784c1c2a7fb51e1cb7d4856c6a22e7
+size 6442451106

model-00069-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0272f186877825828e93c04b41742a6a00685110a0013410c25ef4b69fc9779
+size 427459427

model-00070-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0da09368ad5e312abb9da8c0c71495cee453f23b584a37391b0bdd7b169346
+size 6442451106

model-00075-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00266d57c2c717db1a0b0242683115b2ae3d74e6c061d6bad9ea0ca76ea4608e
+size 6442451104

model-00083-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1817380a51b4bcd7d958d0da8585a6a2e201d4d75b1dd798752af0566238e873
+size 6442451104

model-00086-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4d79a9eccf7f821c4d1d64cc028d77419eab10c2c6498e740a447a53cc83ae
+size 6442451106

model-00088-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3158edb694086df68672c13ac7235900f541470a0c6d7c6725bda2c1bfdc37
+size 6442451106

model-00110-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c357023134fc8b0d88705387cfff5af03227a97ec5e1047357bb801ffc23dd4
+size 6442451106

model-00115-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c42edcdd03f829f4c5e7baee1b1c620dca0a3daecef8c9106af95c9543a6fe
+size 6442451104

model-00122-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9da5af453ba7b837c1bab6a18ed47faa207b13749a52047c7abb1e11edc134b
+size 6442451106

model-00126-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5588109a3f601dcd4df15553fc540a5cdd7e7824c5c7920fa47ef7cda4ebe36c
+size 6442451106

model-00127-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69d1397ec699e338d7a6aca8f5baf3e69daa5a9f9eaef5010e7dbbbc768d477
+size 6442451104

model-00128-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cda82ff1b9638f44f0d999e455db013bd7d0cd510b87280306f0cb463f0cc6
+size 6442451106

model-00134-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8699c7495b52bec934885711c4abc94213af7c92a4149114ada74a1ea4f7b3a
+size 6442451106

model-00151-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1e2e777fa11e3f8413ed3bc6755cf406d63c98401ca02a14940b309806cc3f
+size 6442451104

model-00154-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19670585a4791b2eec7616217939a7ead18453bffa5046f397f214f2120b31ba
+size 6442451106

model-00166-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f884aba54f19d3fad63941f50775e4ab00cde5fa6312f8bd263a1a6c17ecc0d4
+size 6442451106

model-00169-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa57efcefdcd8d30a6ae3001c9d2eddaa11b4c867574a43da13e67683f6512d
+size 427459437

model-00191-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a76f0c188a2087a94d59ce3dc9064491fe0135bc4d0e8f7b9197520137a2509
+size 6442451104

model-00195-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77011a1c668ffa487e99c48d65f8bfcdfd1bb1539b1052d94743e0d0b6351019
+size 6442451104

model-00202-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf7b0f8bb70b478fd7461295f8d26265f63a3eb4d871d7f771cdfa949308977
+size 6442451106

model-00207-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a612db88aa68d6edbc24080e00e3dc1c659daa70c87ecf8a789c38601fbac3e
+size 6442451104

model-00208-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aaab6d6d764334c6eb3b16d09c05cd999ee4bffe4e6a0f68a1b1f97632f4ae2
+size 6442451106

model-00230-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a9f398d3039dfded5c190c2234248744dbfe5abd6b51f5d68e2ba3eb207eee
+size 6442451106

model-00231-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d9be99ab65874fc8c5a1d8b19d5ae3051207bc0e7bbf20e77c4c4d6ed0dab7
+size 6442451104

model-00234-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab1aa77b1915b24862abf853365afba13ba5a1506d615f9966e59aec18c79c1
+size 6442451106

model-00243-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634fa4f93f6997807b96fabb45f1a4b654b5c63fd7532706cb9c89ad9baabd54
+size 6442451104

model-00246-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bb98421e79fc791e67f6aa12c27b02decf943c0831a75f678ca667adba9c69
+size 6442451106

model-00262-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3313755022af6f0763295aa0db31e6abd2a6db37dac86fe9681a657aecb63938
+size 6442451106

model-00270-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0348da7cbcd269497c30feaa2afc21978053ca3342a70fff9e6ca0eff89fddb
+size 6442451106

model-00271-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c50a543b41f5a0772fbf7b4e8675c44ca6ba2e88a9fe73da5afc0979ec43b74
+size 6442451104

model-00274-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446ea78182145f283ec9529de6b06d5aa9eef918de3cb4a1685160ef74fb7ede
+size 6442451106

model-00282-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ade0dc90fb8fe99b2ae1a92c380061a57b75a89b0be40880547ee5b3801b27d
+size 6442451106

model-00287-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36590997ab83ec2cffd90e50c48214e598a38a6561c5b073fe8701164c9f787
+size 6442451104

model-00288-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a664e81f620ea8c90268ab9e1e9af611e5c7b0112343462cb772a0b384177c5
+size 6442451106

model-00291-of-00301.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a92f3b7d979b13240c5bf1148d2a8f7fe17d5cb10a17f2d00330607f75b6cf
+size 6442451104

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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|>"
+  ],
+  "is_local": true,
+  "model_max_length": 202752,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "glm47"
+}