Add GLM-4.7-Flash-PRISM MLX 4-bit quantization by vMLX

.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 +1,53 @@
+---
+language:
+- en
+- zh
+license: other
+license_name: glm-4-license
+pipeline_tag: text-generation
+tags:
+- mlx
+- glm4
+- moe
+- prism
+- abliterated
+- 4bit
+- quantized
+- apple-silicon
+library_name: mlx
+base_model: Ex0bit/GLM-4.7-Flash-PRISM
+---
+
+# GLM-4.7-Flash-PRISM — MLX 4-bit
+
+MLX 4-bit quantized version of [Ex0bit/GLM-4.7-Flash-PRISM](https://huggingface.co/Ex0bit/GLM-4.7-Flash-PRISM) for efficient local inference on Apple Silicon.
+
+- **Quantization**: 4-bit (4.5 bits per weight, group size 64, affine mode)
+- **Architecture**: GLM-4 MoE Lite — 47 layers, 64 routed experts, 4 active per token
+- **Context**: 202K tokens
+- **Size**: ~16 GB
+
+## Usage
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("shieldstackllc/GLM-4.7-Flash-PRISM-mlx-4bit")
+response = generate(model, tokenizer, prompt="Hello!", verbose=True)
+```
+
+Or with [vMLX](https://vmlx.net) for native macOS inference.
+
+## About
+
+This model is an abliterated (uncensored) variant of GLM-4.7-Flash, a Mixture-of-Experts language model by Zhipu AI / THUDM. The abliteration was done by [Ex0bit](https://huggingface.co/Ex0bit) as part of the PRISM series. MLX quantization by [vMLX](https://vmlx.net).
+
+## Also Available
+
+- [GLM-4.7-Flash-PRISM MLX 8-bit](https://huggingface.co/shieldstackllc/GLM-4.7-Flash-PRISM-mlx-8bit) (~30 GB)
+
+## Credits
+
+- **Base model**: [THUDM/GLM-4](https://github.com/THUDM/GLM-4) by Zhipu AI
+- **Abliteration**: [Ex0bit/GLM-4.7-Flash-PRISM](https://huggingface.co/Ex0bit/GLM-4.7-Flash-PRISM)
+- **MLX conversion**: [vMLX](https://vmlx.net) — Run AI locally on Mac. No compromises.

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 +1,114 @@
+{
+    "architectures": [
+        "Glm4MoeLiteForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        154820,
+        154827,
+        154829
+    ],
+    "first_k_dense_replace": 1,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 202752,
+    "mlp_layer_types": [
+        "dense",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse",
+        "sparse"
+    ],
+    "model_type": "glm4_moe_lite",
+    "moe_intermediate_size": 1536,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 20,
+    "num_experts_per_tok": 4,
+    "num_hidden_layers": 47,
+    "num_key_value_heads": 20,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 154820,
+    "partial_rotary_factor": 1.0,
+    "pretraining_tp": 1,
+    "q_lora_rank": 768,
+    "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": {
+        "partial_rotary_factor": 1.0,
+        "rope_theta": 1000000,
+        "rope_type": "default"
+    },
+    "routed_scaling_factor": 1.8,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "transformers_version": "5.0.0.dev0",
+    "use_cache": true,
+    "v_head_dim": 256,
+    "vocab_size": 154880
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4708872bb1235688b69689e7518a7efbcb1b93a4a52781d39b08645e2381a1ae
+size 5357453035

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cef9a13f14a672405801f18310c02c30829eb02cc8676c4a95a7b266d97b4e6
+size 5363462379

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d44c9cb744afb4e341a9c7cb0ae0d15f53e87ffe2675244e4a3d0b130d1c9b
+size 5363462333

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24febc0e481da671da81209584f355f97e45c4e1ccb03d69fc1f1d6692a8478
+size 768064072

tokenizer.json

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

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": 128000,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "glm47"
+}