diff --git a/models/cerebras/zai-glm-4.7.yaml b/models/cerebras/zai-glm-4.7.yaml new file mode 100644 index 0000000..e199c7b --- /dev/null +++ b/models/cerebras/zai-glm-4.7.yaml @@ -0,0 +1,85 @@ +# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json +provider: cerebras +authType: api_key +model: zai-glm-4.7 +params: + - path: max_completion_tokens + type: integer + label: Max tokens + description: Maximum number of output tokens the model may generate, including reasoning tokens. + range: + min: 1 + group: generation_length + - path: temperature + type: number + label: Temperature + description: Controls randomness. Lower values make outputs more focused; higher values make them more varied. Adjust this or top_p, not both. + range: + min: 0 + max: 2 + step: 0.1 + group: sampling + - path: top_p + type: number + label: Top P + description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability. + range: + min: 0 + max: 1 + step: 0.01 + group: sampling + - path: frequency_penalty + type: number + label: Frequency penalty + description: Penalizes tokens by how often they have appeared, reducing verbatim repetition. + default: 0 + range: + min: -2 + max: 2 + step: 0.1 + group: sampling + - path: presence_penalty + type: number + label: Presence penalty + description: Penalizes tokens that have already appeared, encouraging the model to introduce new topics. + default: 0 + range: + min: -2 + max: 2 + step: 0.1 + group: sampling + - path: seed + type: integer + label: Seed + description: Seed used for best-effort deterministic sampling when reproducible outputs are desired. + group: sampling + - path: stop + type: string + label: Stop + description: A string or list of strings where the API will stop generating further tokens. Cerebras accepts up to four stop sequences. + group: generation_length + - path: reasoning_effort + type: enum + label: Reasoning effort + description: Controls how much reasoning the model performs before answering. 'none' disables reasoning. + values: + - none + - low + - medium + - high + group: reasoning + - path: clear_thinking + type: boolean + label: Clear thinking + description: When true, the model's thinking from previous turns is excluded from the conversation context; when false, it is preserved, which is useful for agentic workflows. + default: true + group: reasoning + - path: response_format.type + type: enum + label: Response format + description: Forces the response into plain text or a JSON object. + default: text + values: + - text + - json_object + group: output_format diff --git a/src/data/logos.ts b/src/data/logos.ts index dad3658..e539d86 100644 --- a/src/data/logos.ts +++ b/src/data/logos.ts @@ -29,6 +29,7 @@ const SLUG_TO_LOBE: Record = { alibaba: "alibabacloud-color", "z-ai": "zai", groq: "groq", + cerebras: "cerebras-color", }; const cache = new Map();