modelparams 0.0.12__tar.gz → 0.0.14__tar.gz

{modelparams-0.0.12 → modelparams-0.0.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: modelparams
-Version: 0.0.12
+Version: 0.0.14
 Summary: Typed model parameters for Python, generated from the modelparams.dev catalog.
 Project-URL: Homepage, https://modelparams.dev
 Project-URL: Repository, https://github.com/mnfst/modelparameters.dev

{modelparams-0.0.12 → modelparams-0.0.14}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "modelparams"
-version = "0.0.12"
+version = "0.0.14"
 description = "Typed model parameters for Python, generated from the modelparams.dev catalog."
 readme = "README.md"
 requires-python = ">=3.10"

{modelparams-0.0.12 → modelparams-0.0.14}/src/modelparams/_generated/catalog.json

@@ -628,6 +628,81 @@
       }
     ]
   },
+  {
+    "provider": "alibaba",
+    "authType": "api_key",
+    "model": "qwen3.8-2.4t-a95b",
+    "params": [
+      {
+        "path": "max_completion_tokens",
+        "label": "Max tokens",
+        "description": "Maximum number of tokens to generate, including both reasoning and the final answer.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      },
+      {
+        "path": "temperature",
+        "label": "Temperature",
+        "description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied.",
+        "group": "sampling",
+        "type": "number",
+        "range": {
+          "min": 0,
+          "max": 2,
+          "step": 0.1
+        }
+      },
+      {
+        "path": "top_p",
+        "label": "Top P",
+        "description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.",
+        "group": "sampling",
+        "type": "number",
+        "range": {
+          "min": 0,
+          "max": 1,
+          "step": 0.01
+        }
+      },
+      {
+        "path": "extra_body.top_k",
+        "label": "Top K",
+        "description": "Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling.",
+        "group": "sampling",
+        "type": "integer",
+        "default": 20,
+        "range": {
+          "min": 0
+        }
+      },
+      {
+        "path": "extra_body.enable_thinking",
+        "label": "Enable thinking",
+        "description": "Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients.",
+        "group": "reasoning",
+        "type": "boolean",
+        "default": true
+      },
+      {
+        "path": "extra_body.thinking_budget",
+        "label": "Thinking budget",
+        "description": "Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.",
+        "group": "reasoning",
+        "applicability": {
+          "only": {
+            "extra_body.enable_thinking": true
+          }
+        },
+        "type": "integer",
+        "range": {
+          "min": 1
+        }
+      }
+    ]
+  },
   {
     "provider": "alibaba",
     "authType": "api_key",
@@ -7944,6 +8019,102 @@
       }
     ]
   },
+  {
+    "provider": "google",
+    "authType": "api_key",
+    "model": "gemini-3.7-flash",
+    "params": [
+      {
+        "path": "generationConfig.maxOutputTokens",
+        "label": "Max output tokens",
+        "description": "Maximum number of tokens to include in a response candidate.",
+        "group": "generation_length",
+        "type": "integer",
+        "range": {
+          "min": 1,
+          "max": 65536
+        }
+      },
+      {
+        "path": "generationConfig.temperature",
+        "label": "Temperature",
+        "description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied.",
+        "group": "sampling",
+        "type": "number",
+        "default": 1,
+        "range": {
+          "min": 0,
+          "max": 2,
+          "step": 0.1
+        }
+      },
+      {
+        "path": "generationConfig.topP",
+        "label": "Top P",
+        "description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.",
+        "group": "sampling",
+        "type": "number",
+        "default": 0.95,
+        "range": {
+          "min": 0,
+          "max": 1,
+          "step": 0.01
+        }
+      },
+      {
+        "path": "generationConfig.topK",
+        "label": "Top K",
+        "description": "Limits token sampling to the top K most likely next tokens.",
+        "group": "sampling",
+        "type": "integer",
+        "default": 64,
+        "range": {
+          "min": 0
+        }
+      },
+      {
+        "path": "generationConfig.seed",
+        "label": "Seed",
+        "description": "Optional seed used for decoding when reproducible sampling is desired.",
+        "group": "sampling",
+        "type": "integer"
+      },
+      {
+        "path": "generationConfig.thinkingConfig.thinkingLevel",
+        "label": "Thinking level",
+        "description": "Controls Gemini 3.1 Flash-Lite reasoning effort.",
+        "group": "reasoning",
+        "type": "enum",
+        "default": "minimal",
+        "values": [
+          "minimal",
+          "low",
+          "medium",
+          "high"
+        ]
+      },
+      {
+        "path": "generationConfig.thinkingConfig.includeThoughts",
+        "label": "Include thoughts",
+        "description": "Controls whether Gemini returns available thought summaries in the response parts.",
+        "group": "reasoning",
+        "type": "boolean",
+        "default": false
+      },
+      {
+        "path": "generationConfig.responseMimeType",
+        "label": "Response MIME type",
+        "description": "MIME type for generated text candidates.",
+        "group": "output_format",
+        "type": "enum",
+        "default": "text/plain",
+        "values": [
+          "text/plain",
+          "application/json"
+        ]
+      }
+    ]
+  },
   {
     "provider": "google",
     "authType": "api_key",

{modelparams-0.0.12 → modelparams-0.0.14}/src/modelparams/_generated/model_ids.py

@@ -14,6 +14,7 @@ ModelId = Literal[
     "alibaba/qwen3.6-flash",
     "alibaba/qwen3.7-max",
     "alibaba/qwen3.7-plus",
+    "alibaba/qwen3.8-2.4t-a95b",
     "alibaba/qwen3.8-max",
     "alibaba/qwq-plus",
     "anthropic/claude-3-5-haiku-20241022",
@@ -82,6 +83,7 @@ ModelId = Literal[
     "google/gemini-3.1-flash-lite-subscription",
     "google/gemini-3.1-pro-preview-subscription",
     "google/gemini-3.5-flash",
+    "google/gemini-3.7-flash",
     "google/gemini-flash-latest",
     "google/gemma-3-12b-it",
     "google/gemma-3-1b-it",
@@ -271,6 +273,7 @@ MODEL_IDS: tuple[ModelId, ...] = (
     "alibaba/qwen3.6-flash",
     "alibaba/qwen3.7-max",
     "alibaba/qwen3.7-plus",
+    "alibaba/qwen3.8-2.4t-a95b",
     "alibaba/qwen3.8-max",
     "alibaba/qwq-plus",
     "anthropic/claude-3-5-haiku-20241022",
@@ -339,6 +342,7 @@ MODEL_IDS: tuple[ModelId, ...] = (
     "google/gemini-3.1-flash-lite-subscription",
     "google/gemini-3.1-pro-preview-subscription",
     "google/gemini-3.5-flash",
+    "google/gemini-3.7-flash",
     "google/gemini-flash-latest",
     "google/gemma-3-12b-it",
     "google/gemma-3-1b-it",

{modelparams-0.0.12 → modelparams-0.0.14}/src/modelparams/_generated/registry.py

@@ -35,6 +35,7 @@ PARAM_TYPES: dict[ModelId, Any] = {
     "alibaba/qwen3.6-flash": alibaba.Qwen3_6_FlashParams,
     "alibaba/qwen3.7-max": alibaba.Qwen3_7_MaxParams,
     "alibaba/qwen3.7-plus": alibaba.Qwen3_7_PlusParams,
+    "alibaba/qwen3.8-2.4t-a95b": alibaba.Qwen3_8_2_4t_A95bParams,
     "alibaba/qwen3.8-max": alibaba.Qwen3_8_MaxParams,
     "alibaba/qwq-plus": alibaba.Qwq_PlusParams,
     "anthropic/claude-3-5-haiku-20241022": anthropic.Claude_3_5_Haiku_20241022Params,
@@ -103,6 +104,7 @@ PARAM_TYPES: dict[ModelId, Any] = {
     "google/gemini-3.1-flash-lite-subscription": google.Gemini_3_1_Flash_Lite_SubscriptionParams,
     "google/gemini-3.1-pro-preview-subscription": google.Gemini_3_1_Pro_Preview_SubscriptionParams,
     "google/gemini-3.5-flash": google.Gemini_3_5_FlashParams,
+    "google/gemini-3.7-flash": google.Gemini_3_7_FlashParams,
     "google/gemini-flash-latest": google.Gemini_Flash_LatestParams,
     "google/gemma-3-12b-it": google.Gemma_3_12b_ItParams,
     "google/gemma-3-1b-it": google.Gemma_3_1b_ItParams,

{modelparams-0.0.12 → modelparams-0.0.14}/src/modelparams/types/alibaba.py

@@ -141,6 +141,20 @@ Qwen3_7_PlusParams = TypedDict(
 )
 setattr(Qwen3_7_PlusParams, "__pydantic_config__", _PARAMS_CONFIG)
 
+Qwen3_8_2_4t_A95bParams = TypedDict(
+    "Qwen3_8_2_4t_A95bParams",
+    {
+        "max_completion_tokens": Annotated[int, Field(ge=1)],
+        "temperature": Annotated[float, Field(ge=0, le=2)],
+        "top_p": Annotated[float, Field(ge=0, le=1)],
+        "extra_body.top_k": Annotated[int, Field(ge=0)],
+        "extra_body.enable_thinking": bool,
+        "extra_body.thinking_budget": Annotated[int, Field(ge=1)],
+    },
+    total=False,
+)
+setattr(Qwen3_8_2_4t_A95bParams, "__pydantic_config__", _PARAMS_CONFIG)
+
 Qwen3_8_MaxParams = TypedDict(
     "Qwen3_8_MaxParams",
     {
@@ -178,6 +192,7 @@ __all__ = [
     "Qwen3_6_FlashParams",
     "Qwen3_7_MaxParams",
     "Qwen3_7_PlusParams",
+    "Qwen3_8_2_4t_A95bParams",
     "Qwen3_8_MaxParams",
     "Qwq_PlusParams",
 ]

{modelparams-0.0.12 → modelparams-0.0.14}/src/modelparams/types/google.py

@@ -202,6 +202,22 @@ Gemini_3_5_FlashParams = TypedDict(
 )
 setattr(Gemini_3_5_FlashParams, "__pydantic_config__", _PARAMS_CONFIG)
 
+Gemini_3_7_FlashParams = TypedDict(
+    "Gemini_3_7_FlashParams",
+    {
+        "generationConfig.maxOutputTokens": Annotated[int, Field(ge=1, le=65536)],
+        "generationConfig.temperature": Annotated[float, Field(ge=0, le=2)],
+        "generationConfig.topP": Annotated[float, Field(ge=0, le=1)],
+        "generationConfig.topK": Annotated[int, Field(ge=0)],
+        "generationConfig.seed": int,
+        "generationConfig.thinkingConfig.thinkingLevel": Literal["minimal", "low", "medium", "high"],
+        "generationConfig.thinkingConfig.includeThoughts": bool,
+        "generationConfig.responseMimeType": Literal["text/plain", "application/json"],
+    },
+    total=False,
+)
+setattr(Gemini_3_7_FlashParams, "__pydantic_config__", _PARAMS_CONFIG)
+
 Gemini_Flash_LatestParams = TypedDict(
     "Gemini_Flash_LatestParams",
     {
@@ -373,6 +389,7 @@ __all__ = [
     "Gemini_3_1_Flash_Lite_SubscriptionParams",
     "Gemini_3_1_Pro_Preview_SubscriptionParams",
     "Gemini_3_5_FlashParams",
+    "Gemini_3_7_FlashParams",
     "Gemini_Flash_LatestParams",
     "Gemma_3_12b_ItParams",
     "Gemma_3_1b_ItParams",