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 +1,54 @@
+---
+license: mit
+base_model: Ex0bit/GLM-4.7-PRISM
+model_name: Elbaz-GLM-4.7-PRISM
+tags:
+- abliteration
+- SOTA Abliteration Pipeline - PRISM
+- glm
+- glm4_moe
+- quantized
+- finetuned
+- uncensored
+- abliterated
+- mlx
+- mlx-my-repo
+language:
+- en
+- zh
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# cs2764/GLM-4.7-PRISM-mlx-4Bit
+
+The Model [cs2764/GLM-4.7-PRISM-mlx-4Bit](https://huggingface.co/cs2764/GLM-4.7-PRISM-mlx-4Bit) was converted to MLX format from [Ex0bit/GLM-4.7-PRISM](https://huggingface.co/Ex0bit/GLM-4.7-PRISM) using mlx-lm version **0.30.4**.
+
+## Quantization Details
+
+This model was converted with the following quantization settings:
+
+- **Quantization Strategy**: 4-bit quantization
+- **Average bits per weight**: 4.502
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("cs2764/GLM-4.7-PRISM-mlx-4Bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+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,
+    "dtype": "bfloat16",
+    "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": 0,
+    "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,
+    "transformers_version": "4.57.3",
+    "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": "4.57.3"
+}

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9e28e0ac29735a6c8a96c540fc0edc107db8b942c7f490d1f2557e21cb07b4
+size 5360926927

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851c1358a6c479b8338f9b7278d61ce46e588480eb9fd429fd45884649bfd904
+size 5268767156

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193eb994f48724e37149c2f32affb2eea028ed056f6328117ab5517d99539bdb
+size 5137805027

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2a287f688a911888fe444679d6d5ff3f41d40a2a02914f67517801033644f3
+size 5229445502

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece5ba7d49cbe87a52f262346a873d9feb0be81483c47c204b12508dc17b2977
+size 5137805040

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c3df1f8b54192fa3775eb61661b9d5110cb391bc168e34f12ac9872672f53e
+size 5137805100

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8a5cf4192716cabfd851fdc50f1c04e7dee2064fc79c8f6587ecd4aa688ad5
+size 5229445466

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ae5ac34ea36616181b273cad4a00b698bd4a900abe5b669f6f7b0381bd00d4
+size 5137805116

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc817951ca515cf47ea5ac35bebe448db9901fc9893a4063694bb96d7382ec0
+size 5137805108

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef060c00fd094db55f78f5a22162c79e9e440926b5dbb0bdc90b25a87b0a2b1
+size 5229445506

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ff86532acb535978a97f521897a7c81b263cd2927fa0615b9bdb32f0ce0416
+size 5137805052

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d66dcf5f62b859efc77dcafc3e261309ef0a2ad0fe40ad1f77389ba2229f55
+size 5137805146

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4546bacc8185d1f6b77bc03a6c7dbffe2cde5993c7e9764db987520cdbbf0e03
+size 5229445488

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0ef3c4f9c48228a0d6cbbead141702cf77479ad0c5560b5f7cfd8282275843
+size 5137805116

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2d62c83d66a4dc56a0f44a61b5c8c0c8b98cf30b868a33098fd73eeb36de60
+size 5137805104

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bedb1176bd816fbbf7b9c3250d2e7eca8913b303fc769588e335a6f6bf3a04
+size 5229445468

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eac035010547ada0cc6b9a8a757d59446268b6204e7a9d0b51dcd2f2d243e79
+size 5137805078

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e66aed10de05cc1af558a7c7371cdc05e02d5a978a3033c693ae8fbbc288ea
+size 5137805108

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfa50af9cc844cb379b4534329143e34c2a7888a9841e15e93fd1d9f858bf50
+size 5229445466

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a59e368edc7b50d484869f867b51c3b2d2cb85e6cb6ae54989e335882172d6
+size 5137805112

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0c8038951e323082c8134ba2bc37cc03f37161a4520c4ac1383f8b52565fec
+size 5137805076

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dda634c13b337e0669c347362833eac39d0c68103aa114b468530291a9448bb
+size 5229445422

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11228fcf9ef93a248c96d0178432591bdc9467950328d890efcfd47a02651a98
+size 5137805120

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded4dabced1201425b5c24fea9ecaf37bf8cc04b73326031be3920456838f30a
+size 5137805152

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a657dba2f483f3bc1718664b978dabd2ff701953e5c2e34810a2ba02906bf7
+size 5229445410

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae31453bf8349e10643b6ae679eab2b3bc86391cc06dd627dfe032f439636c3f
+size 5137805084

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c143df01a75df46111a9b4842c1e41c6931b23d38fcece6c3479615d1d5778c5
+size 5137805090

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df7ed08d516a2bccba3063cdead7e146101e1a7fb04706a007bf2fea2484679
+size 5229445482

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b0c26b89d6531fb56526494a39e94d62ae4f5acb4406898bcb2bb479bcfac3
+size 5137805080

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352bf8cff0996fced6e287f1d3f5a73e2da750bf6c643bb699d5932d7f34fa87
+size 5137805150

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa558934ccbf7bc41091fc534dd2702f8bcebbd21493dd44401581607d4684d
+size 5229445498

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1a8e35eae711821e3fc4d2c3f6327ac34407617ea9768853bc09360d3551cc
+size 5137805092

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd78b549108b19d57b32ea42c13382eb16d5892cc0c8a1970c169a67ee781b29
+size 5137805098

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e90f5cfd8006663f9064468ef439915bc5a3698cb8c2a5951ea8540ac70ddd
+size 5229445500

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f60bec6963fe4769678e0e5df731f8c734f121e2fa16cc8f411811ceecd005
+size 5137805124

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481674dafb0678878f1b6db32978d21da1c751269700154f7ed78c8979c93cd4
+size 5137805150

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e711d0cdedb56edb831af3aadc2f71d5f7585fff06ccc66a16e7d3ec8ebfc541
+size 5229445492

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93892b4c72d15a6814ecea992da80b9aa8e1c8e745701346d6b311cc804d16b
+size 5137805114

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b02f76fb66b429f137e129d81ece21379796cacd1555871dbd8a4e1342dac5
+size 1866990890

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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|>",
+    "<think>",
+    "</think>"
+  ],
+  "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|>",
+    "<think>",
+    "</think>"
+  ],
+  "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"
+}