Skip to content

Qwen2_5_Coder_32B_Instruct_Prompt

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5166

optional frequency_penalty: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5211

Decreases the likelihood of the model repeating the same lines verbatim.


optional lora: string

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5174

Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model.


optional max_tokens: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5187

The maximum number of tokens to generate in the response.


optional presence_penalty: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5215

Increases the likelihood of the model introducing new topics.


prompt: string

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5170

The input text prompt for the model to generate a response.


optional raw: boolean

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5179

If true, a chat template is not applied and you must adhere to the specific model’s expected formatting.


optional repetition_penalty: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5207

Penalty for repeated tokens; higher values discourage repetition.


optional response_format: JSONMode

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5175


optional seed: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5203

Random seed for reproducibility of the generation.


optional stream: boolean

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5183

If true, the response will be streamed back incrementally using SSE, Server Sent Events.


optional temperature: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5191

Controls the randomness of the output; higher values produce more random results.


optional top_k: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5199

Limits the AI to choose from the top ‘k’ most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises.


optional top_p: number

Defined in: .pnpm-home/store/v11/links/@cloudflare/workers-types/4.20251118.0/2891147a4db443bf13ca098dcb7381fb6bac5793758b7fd187ebaf5bc0deb969/node_modules/@cloudflare/workers-types/index.ts:5195

Adjusts the creativity of the AI’s responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses.