@bendyline/gezel-inference 0.0.0-stage → 1.0.0

package/dist/catalog/chat-models/ge/gemma4-12b-q4/manifest.json

@@ -0,0 +1,249 @@
+{
+  "schemaVersion": 1,
+  "kind": "chat-model",
+  "id": "gemma4-12b-q4",
+  "name": "Gemma 4 (12B, Q4)",
+  "description": "Google's Gemma 4 at 12B parameters — an encoder-free unified multimodal model (text + image + audio + video) with native tool calling, configurable thinking, and a 256K context window. Apache-2.0 licensed.",
+  "tags": [
+    "google",
+    "multimodal",
+    "vision",
+    "audio",
+    "tools",
+    "agentic",
+    "qat"
+  ],
+  "category": "general",
+  "maintainer": {
+    "name": "Google",
+    "url": "https://huggingface.co/google/gemma-4-12B-it"
+  },
+  "version": "1.2.0",
+  "updatedAt": "2026-08-28T00:00:00Z",
+  "license": "Apache-2.0",
+  "licenseClass": "open",
+  "licenseShortName": "Apache 2.0",
+  "recoScore": 15,
+  "parameterSize": "12B",
+  "approxSizeBytes": 6716356800,
+  "supportsTools": true,
+  "contextWindow": 256000,
+  "upstream": "https://huggingface.co/google/gemma-4-12B-it",
+  "style": {
+    "family": "gemma",
+    "reasoningFormat": "channel",
+    "toolCallFormat": "function-call"
+  },
+  "behaviors": [
+    "reasoning.strip-channel-tags",
+    "reasoning.capture-pre-tool-prose",
+    "prompt.private-reasoning-guidance",
+    "prompt.tool-cookbook-full",
+    "prompt.meester-build-prelude",
+    "fabrication.detect-past-tense-no-tools",
+    "fabrication.detect-claim-without-tool",
+    "turn.preamble-folding",
+    {
+      "id": "turn.ramble-detection",
+      "config": {
+        "coldThreshold": 6000,
+        "postActionThreshold": 1200
+      }
+    },
+    "turn.auto-acknowledge-tool-errors",
+    "turn.permission-stall",
+    {
+      "id": "turn.continuation-budget",
+      "config": {
+        "count": 4
+      }
+    },
+    {
+      "id": "turn.single-tool-per-turn",
+      "config": {
+        "meesterOnly": true
+      }
+    },
+    "mcp.compact-tool-schemas",
+    "mcp.relax-required-fields",
+    "mcp.default-missing-fields",
+    "mcp.validate-ids-strict",
+    "parse.gemma-special-token",
+    "prompt.prefer-writefile-edits",
+    "prompt.derive-by-execution",
+    "prompt.terse-visible-reply",
+    "tools.mlx-grammar"
+  ],
+  "tuning": {
+    "sampling": {
+      "temperature": 1,
+      "topP": 0.95,
+      "topK": 64,
+      "repetitionPenalty": 1.1,
+      "repetitionContext": 64,
+      "maxTokens": 8192
+    },
+    "reasoning": {
+      "enableThinking": true,
+      "thinkingBudget": 2048
+    },
+    "profiles": {
+      "thinking-general": {
+        "sampling": {
+          "temperature": 0.8,
+          "topP": 0.95,
+          "topK": 64,
+          "repetitionPenalty": 1.1,
+          "repetitionContext": 64,
+          "maxTokens": 4096
+        }
+      },
+      "thinking-coding": {
+        "sampling": {
+          "temperature": 0.6,
+          "topP": 0.9,
+          "topK": 40,
+          "repetitionPenalty": 1.05,
+          "repetitionContext": 64,
+          "maxTokens": 4096
+        }
+      },
+      "thinking-precise": {
+        "sampling": {
+          "temperature": 0.3,
+          "topP": 0.9,
+          "topK": 20,
+          "repetitionPenalty": 1.05,
+          "repetitionContext": 64,
+          "maxTokens": 4096,
+          "seed": 0
+        }
+      },
+      "instruct": {
+        "sampling": {
+          "temperature": 0.7,
+          "topP": 0.95,
+          "topK": 64,
+          "repetitionPenalty": 1.1,
+          "repetitionContext": 64,
+          "maxTokens": 4096
+        }
+      },
+      "creative": {
+        "sampling": {
+          "temperature": 1.1,
+          "topP": 0.95,
+          "topK": 64,
+          "repetitionPenalty": 1,
+          "repetitionContext": 20,
+          "maxTokens": 8192
+        }
+      }
+    },
+    "engine": {
+      "llamaCpp": {
+        "spec": {
+          "mtp": true,
+          "nMax": 4
+        }
+      }
+    }
+  },
+  "evalHints": {
+    "sniffThresholds": {
+      "inlineJsMinBytes": 1000
+    }
+  },
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/gemma-4-12B-it-qat-GGUF",
+    "revision": "980b060c40a8539ac159e0501a3e0f66a6365af3",
+    "filename": "gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
+    "sha256": "90fd44e29e0d7cffeb0fd00dc73cfdab9ed0b0e95306ecf7821ea634c940c370",
+    "approxSizeBytes": 6716356800,
+    "quantization": "UD-Q4_K_XL",
+    "draftModel": {
+      "filename": "MTP/mtp-gemma-4-12B-it-Q4_0.gguf",
+      "sha256": "fcb35dea42c71333db904cee11baac525c9ef872818ee3753f6cb156f3c6f4f6",
+      "sizeBytes": 253708800
+    }
+  },
+  "mlx": {
+    "huggingfaceRepo": "OsaurusAI/gemma-4-12B-it-qat-MXFP4",
+    "revision": "61fbdd1be971d8808060d8ba4e607f420125b214",
+    "quantization": "MXFP4",
+    "approxSizeBytes": 7942602298,
+    "files": [
+      {
+        "name": "chat_template.jinja",
+        "sha256": "d5ce49ce670058e90cc623c0284c21c8fcd778c30f5be1891b00f022bedee2fe",
+        "sizeBytes": 17811
+      },
+      {
+        "name": "config.json",
+        "sha256": "7052f31177bb79e2c6760d5032583f74c1864eb51b5a17e1404a10eca3acf913",
+        "sizeBytes": 5237
+      },
+      {
+        "name": "generation_config.json",
+        "sha256": "a8349d9bd64cc5841297fcb5002f0fdc4749c473c8f1b10ea337f9ce4ee7014e",
+        "sizeBytes": 260
+      },
+      {
+        "name": "model-00001-of-00007.safetensors",
+        "sha256": "8bbc6b27a2127ca6d68a449ff895644cd18477cc69205c4cd02907b862c4cf11",
+        "sizeBytes": 2047672664
+      },
+      {
+        "name": "model-00002-of-00007.safetensors",
+        "sha256": "5794202f68df90c7f18a6db80a9a273235146f1d1b05f632e7df1ed1644996a7",
+        "sizeBytes": 1023076042
+      },
+      {
+        "name": "model-00003-of-00007.safetensors",
+        "sha256": "299ff6ced2b6b8e4d0957bc4b4f26e7fbd25b3917bc0a9f27dd8d983449241b9",
+        "sizeBytes": 1012218216
+      },
+      {
+        "name": "model-00004-of-00007.safetensors",
+        "sha256": "1f0e6f655d2a59d2e3b0d987f705e498be535f6c9782c9726c3e37ede1c55545",
+        "sizeBytes": 1009437650
+      },
+      {
+        "name": "model-00005-of-00007.safetensors",
+        "sha256": "06d4b763d2bba8277e78d6a1bcd2a623190956da8adfb6d7e2fdd3234bc213a8",
+        "sizeBytes": 1024911496
+      },
+      {
+        "name": "model-00006-of-00007.safetensors",
+        "sha256": "ecdb96e03cba6751e3d73d621019afd20e4b9040162997e1e236e7231793370a",
+        "sizeBytes": 1018677986
+      },
+      {
+        "name": "model-00007-of-00007.safetensors",
+        "sha256": "1aa3cfd784f63827f6ec9eb0b2a98f735976deb62ead0a54b87f33aba7f96176",
+        "sizeBytes": 774295738
+      },
+      {
+        "name": "model.safetensors.index.json",
+        "sha256": "136ff8d0fb292d5cd6688d7a5456b7710a2d4628c53947b45180e3dc654697c2",
+        "sizeBytes": 97771
+      },
+      {
+        "name": "processor_config.json",
+        "sha256": "6b938e76555b3e9946890770e1abcd442a4718f34041a58e8139dc8ad34545c9",
+        "sizeBytes": 1382
+      },
+      {
+        "name": "tokenizer.json",
+        "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+        "sizeBytes": 32169626
+      },
+      {
+        "name": "tokenizer_config.json",
+        "sha256": "c0146b8149eb8b8f96e9b92b9a0d5e0d1864140b49a4d13cec52bc9adcecb5a7",
+        "sizeBytes": 20419
+      }
+    ],
+    "chatTemplateOverride": "{#\n  Template: Google Gemma 4 Canonical Chat Template\n  Author: Google Gemma Engineering Team\n  Published: 2026-07-09\n  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.\n#}\n{%- macro format_parameters(properties, required, filter_keys=false) -%}\n    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n    {%- set ns = namespace(found_first=false) -%}\n    {%- for key, value in properties | dictsort -%}\n        {%- set add_comma = false -%}\n        {%- if not filter_keys or key not in standard_keys -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {{ key }}:{\n            {%- if value['description'] -%}\n                description:<|\"|>{{ value['description'] }}<|\"|>\n                {%- set add_comma = true -%}\n            {%- endif -%}\n            {%- if value['type'] | upper == 'STRING' -%}\n                {%- if value['enum'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    enum:{{ format_argument(value['enum']) }}\n                {%- endif -%}\n            {%- elif value['type'] | upper == 'ARRAY' -%}\n                {%- if value['items'] is mapping and value['items'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    items:{\n                    {%- set ns_items = namespace(found_first=false) -%}\n                    {%- for item_key, item_value in value['items'] | dictsort -%}\n                        {%- if item_value is not none -%}\n                            {%- if ns_items.found_first %},{% endif -%}\n                            {%- set ns_items.found_first = true -%}\n                            {%- if item_key == 'properties' -%}\n                                properties:{\n                                {%- if item_value is mapping -%}\n                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n                                {%- endif -%}\n                                }\n                            {%- elif item_key == 'required' -%}\n                                required:[\n                                {%- for req_item in item_value -%}\n                                    <|\"|>{{- req_item -}}<|\"|>\n                                    {%- if not loop.last %},{% endif -%}\n                                {%- endfor -%}\n                                ]\n                            {%- elif item_key == 'type' -%}\n                                {%- if item_value is string -%}\n                                    type:{{ format_argument(item_value | upper) }}\n                                {%- else -%}\n                                    type:{{ format_argument(item_value | map('upper') | list) }}\n                                {%- endif -%}\n                            {%- else -%}\n                                {{ item_key }}:{{ format_argument(item_value) }}\n                            {%- endif -%}\n                        {%- endif -%}\n                    {%- endfor -%}\n                    }\n                {%- endif -%}\n            {%- endif -%}\n            {%- if value['nullable'] %}\n                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                nullable:true\n            {%- endif -%}\n            {%- if value['type'] | upper == 'OBJECT' -%}\n                {%- if value['properties'] is defined and value['properties'] is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n                    }\n                {%- elif value is mapping -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    properties:{\n                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}\n                    }\n                {%- endif -%}\n                {%- if value['required'] -%}\n                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n                    required:[\n                    {%- for item in value['required'] | default([]) -%}\n                        <|\"|>{{- item -}}<|\"|>\n                        {%- if not loop.last %},{% endif -%}\n                    {%- endfor -%}\n                    ]\n                {%- endif -%}\n            {%- endif -%}\n            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n            type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n        {%- endif -%}\n    {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n    declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n    {%- set params = tool_data['function']['parameters'] -%}\n    {%- if params -%}\n        ,parameters:{\n        {%- if params['properties'] -%}\n            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n        {%- endif -%}\n        {%- if params['required'] -%}\n            required:[\n            {%- for item in params['required'] -%}\n                <|\"|>{{- item -}}<|\"|>\n                {{- ',' if not loop.last -}}\n            {%- endfor -%}\n            ],\n        {%- endif -%}\n        {%- if params['type'] -%}\n            type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if 'response' in tool_data['function'] -%}\n        {%- set response_declaration = tool_data['function']['response'] -%}\n        ,response:{\n        {%- if response_declaration['description'] -%}\n            description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n        {%- endif -%}\n        {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n            type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n        {%- endif -%}\n    {%- endif -%}\n    }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n    {%- if argument is none -%}\n        {{- 'null' -}}\n    {%- elif argument is string -%}\n        {{- '<|\"|>' + argument + '<|\"|>' -}}\n    {%- elif argument is boolean -%}\n        {{- 'true' if argument else 'false' -}}\n    {%- elif argument is mapping -%}\n        {{- '{' -}}\n        {%- set ns = namespace(found_first=false) -%}\n        {%- for key, value in argument | dictsort -%}\n            {%- if ns.found_first %},{% endif -%}\n            {%- set ns.found_first = true -%}\n            {%- if escape_keys -%}\n                {{- '<|\"|>' + key + '<|\"|>' -}}\n            {%- else -%}\n                {{- key -}}\n            {%- endif -%}\n            :{{- format_argument(value, escape_keys=escape_keys) -}}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- elif argument is sequence -%}\n        {{- '[' -}}\n        {%- for item in argument -%}\n            {{- format_argument(item, escape_keys=escape_keys) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- ']' -}}\n    {%- else -%}\n        {{- argument -}}\n    {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n    {%- set ns = namespace(result='') -%}\n    {%- for part in text.split('<channel|>') -%}\n        {%- if '<|channel>' in part -%}\n            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n        {%- else -%}\n            {%- set ns.result = ns.result + part -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {{- ns.result | trim -}}\n{%- endmacro -%}\n\n{%- macro format_tool_response_block(tool_name, response) -%}\n    {{- '<|tool_response>' -}}\n    {%- if response is mapping -%}\n        {{- 'response:' + tool_name + '{' -}}\n        {%- for key, value in response | dictsort -%}\n            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n            {%- if not loop.last %},{% endif -%}\n        {%- endfor -%}\n        {{- '}' -}}\n    {%- else -%}\n        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n    {%- endif -%}\n    {{- '<tool_response|>' -}}\n{%- endmacro -%}\n\n{#- ===== SETUP ===== -#}\n{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}\n{%- set loop_messages = messages -%}\n{%- set enable_thinking = enable_thinking | default(false) -%}\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}\n    {{- '<|turn>system\\n' -}}\n    {#- Inject Thinking token at the very top of the FIRST system turn -#}\n    {%- if enable_thinking -%}\n        {{- '<|think|>\\n' -}}\n        {%- set ns.prev_message_type = 'think' -%}\n    {%- endif -%}\n    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}\n        {%- if messages[0]['content'] is string -%}\n            {{- messages[0]['content'] | trim -}}\n        {%- elif messages[0]['content'] is sequence -%}\n            {%- for item in messages[0]['content'] -%}\n                {{- item['text'] | trim + ' '-}}\n            {%- endfor -%}\n        {%- endif -%}\n        {%- set loop_messages = messages[1:] -%}\n    {%- endif -%}\n    {%- if tools -%}\n        {%- for tool in tools %}\n            {{- '<|tool>' -}}\n            {{- format_function_declaration(tool) | trim -}}\n            {{- '<tool|>' -}}\n        {%- endfor %}\n        {%- set ns.prev_message_type = 'tool' -%}\n    {%- endif -%}\n    {{- '<turn|>\\n' -}}\n{%- endif %}\n\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n    {%- if loop_messages[i]['role'] == 'user' -%}\n        {%- set ns_turn.last_user_idx = i -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n    {%- if message['role'] != 'tool' -%}\n    {%- set ns.prev_message_type = None -%}\n    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}\n    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}\n    {%- if not continue_same_model_turn -%}\n        {{- '<|turn>' + role + '\\n' }}\n\n    {%- endif -%}\n\n    {#- Render reasoning/reasoning_content as thinking channel -#}\n    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}\n    {%- if thinking_text and thinking_gate -%}\n        {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n    {%- endif -%}\n\n            {%- if message.get('tool_calls') -%}\n                {%- for tool_call in message.get('tool_calls') -%}\n                    {%- set function = tool_call['function'] -%}\n                    {{- '<|tool_call>call:' + function['name'] + '{' -}}\n                    {%- if function['arguments'] is mapping -%}\n                        {%- set ns_args = namespace(found_first=false) -%}\n                        {%- for key, value in function['arguments'] | dictsort -%}\n                            {%- if ns_args.found_first %},{% endif -%}\n                            {%- set ns_args.found_first = true -%}\n                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n                        {%- endfor -%}\n                    {%- elif function['arguments'] is none -%}\n                    {%- else -%}\n                        {{- raise_exception(\n                            \"chat_template: tool_calls[].function.arguments must be a \"\n                            \"JSON object (mapping), not a string. Deserialize arguments \"\n                            \"before passing to the template.\"\n                        ) -}}\n                    {%- endif -%}\n                    {{- '}<tool_call|>' -}}\n                {%- endfor -%}\n                {%- set ns.prev_message_type = 'tool_call' -%}\n            {%- endif -%}\n\n            {%- set ns_tr_out = namespace(flag=false) -%}\n            {%- if message.get('tool_responses') -%}\n                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n                {%- for tool_response in message.get('tool_responses') -%}\n                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}\n                    {%- set ns_tr_out.flag = true -%}\n                    {%- set ns.prev_message_type = 'tool_response' -%}\n                {%- endfor -%}\n            {%- elif message.get('tool_calls') -%}\n                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n                {%- set ns_tool_scan = namespace(stopped=false) -%}\n                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n                    {%- if ns_tool_scan.stopped -%}\n                    {%- elif loop_messages[k]['role'] != 'tool' -%}\n                        {%- set ns_tool_scan.stopped = true -%}\n                    {%- else -%}\n                        {%- set follow = loop_messages[k] -%}\n                        {#- Resolve tool_call_id to function name -#}\n                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}\n                        {%- for tc in message.get('tool_calls') -%}\n                            {%- if tc.get('id') == follow.get('tool_call_id') -%}\n                                {%- set ns_tname.name = tc['function']['name'] -%}\n                            {%- endif -%}\n                        {%- endfor -%}\n                        {#- Handle content as string or content-parts array -#}\n                        {%- set tool_body = follow.get('content') -%}\n                        {%- if tool_body is string -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- elif tool_body is sequence and tool_body is not string -%}\n                            {%- set ns_txt = namespace(s='') -%}\n                            {%- for part in tool_body -%}\n                                {%- if part.get('type') == 'text' -%}\n                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n                                {%- endif -%}\n                            {%- endfor -%}\n                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n                            {%- for part in tool_body -%}\n                                {%- if part.get('type') in ['image', 'image_url'] -%}\n                                    {{- '<|image|>' -}}\n                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}\n                                    {{- '<|audio|>' -}}\n                                {%- elif part.get('type') == 'video' -%}\n                                    {{- '<|video|>' -}}\n                                {%- endif -%}\n                            {%- endfor -%}\n                        {%- else -%}\n                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n                        {%- endif -%}\n                        {%- set ns_tr_out.flag = true -%}\n                        {%- set ns.prev_message_type = 'tool_response' -%}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n\n            {%- set captured_content -%}\n            {%- if message.get('content') is string -%}\n                {%- if role == 'model' -%}\n                    {{- strip_thinking(message['content']) -}}\n                {%- else -%}\n                    {{- message['content'] | trim -}}\n                {%- endif -%}\n            {%- elif message.get('content') is sequence -%}\n                {%- for item in message['content'] -%}\n                    {%- if item.get('type') == 'text' -%}\n                        {%- if role == 'model' -%}\n                            {{- strip_thinking(item['text']) -}}\n                        {%- else -%}\n                            {{- item['text'] | trim -}}\n                        {%- endif -%}\n                    {%- elif item.get('type') in ['image', 'image_url'] -%}\n                        {{- '<|image|>' -}}\n                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}\n                        {{- '<|audio|>' -}}\n                    {%- elif item.get('type') == 'video' -%}\n                        {{- '<|video|>' -}}\n                    {%- endif -%}\n                {%- endfor -%}\n            {%- endif -%}\n            {%- endset -%}\n\n            {{- captured_content -}}\n            {%- set has_content = captured_content | trim | length > 0 -%}\n\n        {#- Forward-scan: find next non-tool message role for continuation detection -#}\n        {%- set next_nt = namespace(role=None, found=false) -%}\n        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}\n            {%- if not next_nt.found -%}\n                {%- if loop_messages[j]['role'] != 'tool' -%}\n                    {%- set next_nt.role = loop_messages[j]['role'] -%}\n                    {%- set next_nt.found = true -%}\n                {%- endif -%}\n            {%- endif -%}\n        {%- endfor -%}\n\n        {%- set continues_into_next = (\n            role == 'model'\n            and next_nt.role == 'assistant'\n            and (not message.get('tool_calls') or ns_tr_out.flag)\n        ) -%}\n\n        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n            {{- '<|tool_response>' -}}\n        {%- elif continues_into_next -%}\n        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}\n            {{- '<turn|>\\n' -}}\n        {%- endif -%}\n\n    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}\n    {%- set ns.prev_non_tool_role = message['role'] -%}\n    {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n        {{- '<|turn>model\\n' -}}\n        {%- if not enable_thinking -%}\n            {{- '<|channel>thought\\n<channel|>' -}}\n        {%- endif -%}\n    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}\n        {{- '<|channel>thought\\n' -}}\n    {%- endif -%}\n{%- endif -%}\n"
+  }
+}

package/dist/catalog/chat-models/ge/gemma4-12b-q4/versions/1.0.0/manifest.json

@@ -0,0 +1,70 @@
+{
+  "schemaVersion": 1,
+  "version": "1.0.0",
+  "releasedAt": "2026-06-03T00:00:00Z",
+  "approxSizeBytes": 7381382048,
+  "llamaCpp": {
+    "huggingfaceRepo": "ggml-org/gemma-4-12B-it-GGUF",
+    "filename": "gemma-4-12B-it-Q4_K_M.gguf",
+    "sha256": "5cf8a1f2fc4268b3fd628743675910cf1d8137c4742d0be401c3e885f605023a",
+    "approxSizeBytes": 7381382048,
+    "quantization": "Q4_K_M"
+  },
+  "mlx": {
+    "huggingfaceRepo": "mlx-community/gemma-4-12b-it-4bit",
+    "quantization": "4bit",
+    "approxSizeBytes": 11020138856,
+    "files": [
+      {
+        "name": "chat_template.jinja",
+        "sha256": "36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0",
+        "sizeBytes": 17466
+      },
+      {
+        "name": "config.json",
+        "sha256": "a17d0966c7e4be270f5ce096e286935ad4386d8262c9c6d6982e61ed4d50f286",
+        "sizeBytes": 40011
+      },
+      {
+        "name": "generation_config.json",
+        "sha256": "a8349d9bd64cc5841297fcb5002f0fdc4749c473c8f1b10ea337f9ce4ee7014e",
+        "sizeBytes": 260
+      },
+      {
+        "name": "model-00001-of-00003.safetensors",
+        "sha256": "d9b111c56e4326a9b0828c1775e555c9352172ad531c761d25fd2c0680e3a2f5",
+        "sizeBytes": 5343482389
+      },
+      {
+        "name": "model-00002-of-00003.safetensors",
+        "sha256": "e03f5115111add3927847c257de2e6e5143f23113ac70be63d3e9e6ce25b2f38",
+        "sizeBytes": 5315166368
+      },
+      {
+        "name": "model-00003-of-00003.safetensors",
+        "sha256": "7ce14657eeeb296823ac5e7186bdbf1d69f0a5053c7c6ecd7125c708270b9989",
+        "sizeBytes": 329123819
+      },
+      {
+        "name": "model.safetensors.index.json",
+        "sha256": "b87c93774de5d13ca9d0e21b045793e42e5df032fb5e7622212524f56f9695f2",
+        "sizeBytes": 135330
+      },
+      {
+        "name": "processor_config.json",
+        "sha256": "016a1db9c4f41ea0c61919c46855ea5e7c45c6e4ae4bfbedfb5b6bed79a2fe92",
+        "sizeBytes": 868
+      },
+      {
+        "name": "tokenizer.json",
+        "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+        "sizeBytes": 32169626
+      },
+      {
+        "name": "tokenizer_config.json",
+        "sha256": "fc1384a911d2c9860ac07bc3ceafff20bff26695991744b7dbe5e1e4522bfa57",
+        "sizeBytes": 2719
+      }
+    ]
+  }
+}

package/dist/catalog/chat-models/ge/gemma4-12b-q4/versions/1.1.0/manifest.json

@@ -0,0 +1,72 @@
+{
+  "schemaVersion": 1,
+  "version": "1.1.0",
+  "releasedAt": "2026-06-06T00:00:00Z",
+  "approxSizeBytes": 6716355328,
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/gemma-4-12B-it-qat-GGUF",
+    "revision": "ceadd70e5c46c5a839a7fd622307dabe8fdea551",
+    "filename": "gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
+    "sha256": "cc9ff072e0a8203429ed854e6662c17a6c2bc1e5dca5b475dd4736caaacbc165",
+    "approxSizeBytes": 6716355328,
+    "quantization": "UD-Q4_K_XL"
+  },
+  "mlx": {
+    "huggingfaceRepo": "mlx-community/gemma-4-12B-it-qat-4bit",
+    "revision": "e70c6b3ba0979b3357dcd2f223ad8bde7787a6b6",
+    "quantization": "4bit",
+    "approxSizeBytes": 11020138609,
+    "files": [
+      {
+        "name": "chat_template.jinja",
+        "sha256": "36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0",
+        "sizeBytes": 17466
+      },
+      {
+        "name": "config.json",
+        "sha256": "fe091f98e6f7e5e80461bd8ec7ced6d87ac16987586239386ed44b82ecbc2b12",
+        "sizeBytes": 39882
+      },
+      {
+        "name": "generation_config.json",
+        "sha256": "a8349d9bd64cc5841297fcb5002f0fdc4749c473c8f1b10ea337f9ce4ee7014e",
+        "sizeBytes": 260
+      },
+      {
+        "name": "model-00001-of-00003.safetensors",
+        "sha256": "9fc7406175fdfbca0f941767bfa222ecdaea71ab1d2865cd049eb2a0a1d9f2a1",
+        "sizeBytes": 5343482357
+      },
+      {
+        "name": "model-00002-of-00003.safetensors",
+        "sha256": "62a2b9715c9bef3a4f0a2769fe2d5022ae55907b631731a24568f3e8f444d9e9",
+        "sizeBytes": 5315166254
+      },
+      {
+        "name": "model-00003-of-00003.safetensors",
+        "sha256": "fd75a04eb5cc73be2760898715472e92626b0a8ba03b19ee57737419885da6c9",
+        "sizeBytes": 329123819
+      },
+      {
+        "name": "model.safetensors.index.json",
+        "sha256": "b87c93774de5d13ca9d0e21b045793e42e5df032fb5e7622212524f56f9695f2",
+        "sizeBytes": 135330
+      },
+      {
+        "name": "processor_config.json",
+        "sha256": "016a1db9c4f41ea0c61919c46855ea5e7c45c6e4ae4bfbedfb5b6bed79a2fe92",
+        "sizeBytes": 868
+      },
+      {
+        "name": "tokenizer.json",
+        "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+        "sizeBytes": 32169626
+      },
+      {
+        "name": "tokenizer_config.json",
+        "sha256": "a4260621db48fa22f2b09ce3ba5ad0ec0cc0e032aa702e3ab743a0bc9d6e1d06",
+        "sizeBytes": 2747
+      }
+    ]
+  }
+}

package/dist/catalog/chat-models/ge/gemma4-12b-q4/versions/1.1.2/manifest.json

@@ -0,0 +1,78 @@
+{
+  "schemaVersion": 1,
+  "version": "1.1.2",
+  "releasedAt": "2026-07-28T00:00:00Z",
+  "approxSizeBytes": 6716356800,
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/gemma-4-12B-it-qat-GGUF",
+    "revision": "980b060c40a8539ac159e0501a3e0f66a6365af3",
+    "filename": "gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
+    "sha256": "90fd44e29e0d7cffeb0fd00dc73cfdab9ed0b0e95306ecf7821ea634c940c370",
+    "approxSizeBytes": 6716356800,
+    "quantization": "UD-Q4_K_XL",
+    "residentBytes": 8364078720,
+    "draftModel": {
+      "filename": "MTP/mtp-gemma-4-12B-it-Q4_0.gguf",
+      "sha256": "fcb35dea42c71333db904cee11baac525c9ef872818ee3753f6cb156f3c6f4f6",
+      "sizeBytes": 253708800
+    }
+  },
+  "mlx": {
+    "huggingfaceRepo": "mlx-community/gemma-4-12B-it-qat-4bit",
+    "revision": "e70c6b3ba0979b3357dcd2f223ad8bde7787a6b6",
+    "quantization": "4bit",
+    "approxSizeBytes": 11020138609,
+    "files": [
+      {
+        "name": "chat_template.jinja",
+        "sha256": "36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0",
+        "sizeBytes": 17466
+      },
+      {
+        "name": "config.json",
+        "sha256": "fe091f98e6f7e5e80461bd8ec7ced6d87ac16987586239386ed44b82ecbc2b12",
+        "sizeBytes": 39882
+      },
+      {
+        "name": "generation_config.json",
+        "sha256": "a8349d9bd64cc5841297fcb5002f0fdc4749c473c8f1b10ea337f9ce4ee7014e",
+        "sizeBytes": 260
+      },
+      {
+        "name": "model-00001-of-00003.safetensors",
+        "sha256": "9fc7406175fdfbca0f941767bfa222ecdaea71ab1d2865cd049eb2a0a1d9f2a1",
+        "sizeBytes": 5343482357
+      },
+      {
+        "name": "model-00002-of-00003.safetensors",
+        "sha256": "62a2b9715c9bef3a4f0a2769fe2d5022ae55907b631731a24568f3e8f444d9e9",
+        "sizeBytes": 5315166254
+      },
+      {
+        "name": "model-00003-of-00003.safetensors",
+        "sha256": "fd75a04eb5cc73be2760898715472e92626b0a8ba03b19ee57737419885da6c9",
+        "sizeBytes": 329123819
+      },
+      {
+        "name": "model.safetensors.index.json",
+        "sha256": "b87c93774de5d13ca9d0e21b045793e42e5df032fb5e7622212524f56f9695f2",
+        "sizeBytes": 135330
+      },
+      {
+        "name": "processor_config.json",
+        "sha256": "016a1db9c4f41ea0c61919c46855ea5e7c45c6e4ae4bfbedfb5b6bed79a2fe92",
+        "sizeBytes": 868
+      },
+      {
+        "name": "tokenizer.json",
+        "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+        "sizeBytes": 32169626
+      },
+      {
+        "name": "tokenizer_config.json",
+        "sha256": "a4260621db48fa22f2b09ce3ba5ad0ec0cc0e032aa702e3ab743a0bc9d6e1d06",
+        "sizeBytes": 2747
+      }
+    ]
+  }
+}

package/dist/catalog/chat-models/ge/gemma4-12b-q4/versions/1.1.3/manifest.json

@@ -0,0 +1,78 @@
+{
+  "schemaVersion": 1,
+  "version": "1.1.3",
+  "releasedAt": "2026-08-15T00:00:00Z",
+  "approxSizeBytes": 6716356800,
+  "llamaCpp": {
+    "huggingfaceRepo": "unsloth/gemma-4-12B-it-qat-GGUF",
+    "revision": "980b060c40a8539ac159e0501a3e0f66a6365af3",
+    "filename": "gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
+    "sha256": "90fd44e29e0d7cffeb0fd00dc73cfdab9ed0b0e95306ecf7821ea634c940c370",
+    "approxSizeBytes": 6716356800,
+    "quantization": "UD-Q4_K_XL",
+    "draftModel": {
+      "filename": "MTP/mtp-gemma-4-12B-it-Q4_0.gguf",
+      "sha256": "fcb35dea42c71333db904cee11baac525c9ef872818ee3753f6cb156f3c6f4f6",
+      "sizeBytes": 253708800
+    }
+  },
+  "mlx": {
+    "huggingfaceRepo": "mlx-community/gemma-4-12B-it-qat-4bit",
+    "revision": "e70c6b3ba0979b3357dcd2f223ad8bde7787a6b6",
+    "quantization": "4bit",
+    "approxSizeBytes": 11020138609,
+    "files": [
+      {
+        "name": "chat_template.jinja",
+        "sha256": "36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0",
+        "sizeBytes": 17466
+      },
+      {
+        "name": "config.json",
+        "sha256": "fe091f98e6f7e5e80461bd8ec7ced6d87ac16987586239386ed44b82ecbc2b12",
+        "sizeBytes": 39882
+      },
+      {
+        "name": "generation_config.json",
+        "sha256": "a8349d9bd64cc5841297fcb5002f0fdc4749c473c8f1b10ea337f9ce4ee7014e",
+        "sizeBytes": 260
+      },
+      {
+        "name": "model-00001-of-00003.safetensors",
+        "sha256": "9fc7406175fdfbca0f941767bfa222ecdaea71ab1d2865cd049eb2a0a1d9f2a1",
+        "sizeBytes": 5343482357
+      },
+      {
+        "name": "model-00002-of-00003.safetensors",
+        "sha256": "62a2b9715c9bef3a4f0a2769fe2d5022ae55907b631731a24568f3e8f444d9e9",
+        "sizeBytes": 5315166254
+      },
+      {
+        "name": "model-00003-of-00003.safetensors",
+        "sha256": "fd75a04eb5cc73be2760898715472e92626b0a8ba03b19ee57737419885da6c9",
+        "sizeBytes": 329123819
+      },
+      {
+        "name": "model.safetensors.index.json",
+        "sha256": "b87c93774de5d13ca9d0e21b045793e42e5df032fb5e7622212524f56f9695f2",
+        "sizeBytes": 135330
+      },
+      {
+        "name": "processor_config.json",
+        "sha256": "016a1db9c4f41ea0c61919c46855ea5e7c45c6e4ae4bfbedfb5b6bed79a2fe92",
+        "sizeBytes": 868
+      },
+      {
+        "name": "tokenizer.json",
+        "sha256": "cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f",
+        "sizeBytes": 32169626
+      },
+      {
+        "name": "tokenizer_config.json",
+        "sha256": "a4260621db48fa22f2b09ce3ba5ad0ec0cc0e032aa702e3ab743a0bc9d6e1d06",
+        "sizeBytes": 2747
+      }
+    ]
+  },
+  "minGezelVersion": "1.26227"
+}