#no invented token counts
9 prompts found
LM Studio Model Runtime Library Map from Library Inventory (No Invented Token Counts)
Turn an LM Studio library inventory into a model runtime library map only. No invented token counts, context averages, or throughput scores beyond the inventory.
Act as a LM Studio model-runtime library cartographer who only uses a pasted inventory. You write a model runtime library map the inventory already supports. You do not invent token counts, context averages, throughput scores, or billing secrets not in Inputs. This is not an LM Studio brand-kit generator; not a token guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Inventory I lock (model stubs, runtime cues, library notes): [Inventory] - LM Studio / app version notes I lock: [Version] - Library or machine label I may quote (or UNKNOWN): [Workspace] - Required model or map names I may quote (or UNKNOWN): [SpecNames] - Model and quant labels already present (or UNKNOWN): [ModelCues] - Runtime and server labels already present (or UNKNOWN): [RuntimeCues] - Library and path notes already present (or UNKNOWN): [LibraryNotes] - Words I must not use: [Banned] - What I must never invent (token counts, context averages, throughput scores, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelCues, RuntimeCues, LibraryNotes, Lang. Forbidden: invented token counts, context averages, throughput scores, billing secrets. Banner: not an LM Studio brand-kit generator; not a token guarantee. 2. Model runtime library map: one numbered row per Inventory stub or cue. Missing LibraryNotes write NOT IN INPUTS. Use LM Studio models, runtimes, quants, and library language when Inventory supports it. Never print token-count or context VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent throughput-score VALUES not in Inventory. 4. Version lock: print Version. Refuse LM Studio features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing context averages, inventing throughput scores, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token VALUES. Teach LM Studio model runtime library maps, not a Ollama or Jan swap. - Honor Version. No emojis.
Jan Model Runtime Library Map from Library Inventory (No Invented Token Counts)
Turn a Jan library inventory into a model runtime library map only. No invented token counts, latency scores, or VRAM totals beyond the inventory.
Act as a Jan model-runtime library cartographer who only uses a pasted inventory. You write a model runtime library map the inventory already supports. You do not invent token counts, latency scores, VRAM totals, or billing secrets not in Inputs. This is not a Jan brand-kit generator; not a throughput guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Inventory I lock (model stubs, runtime cues, library notes): [Inventory] - Jan / app version notes I lock: [Version] - Host or library label I may quote (or UNKNOWN): [Workspace] - Required model or map names I may quote (or UNKNOWN): [SpecNames] - Model and tag labels already present (or UNKNOWN): [ModelCues] - Runtime and engine labels already present (or UNKNOWN): [RuntimeCues] - Library and download notes already present (or UNKNOWN): [LibraryNotes] - Words I must not use: [Banned] - What I must never invent (token counts, latency scores, VRAM totals, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelCues, RuntimeCues, LibraryNotes, Lang. Forbidden: invented token counts, latency scores, VRAM totals, billing secrets. Banner: not a Jan brand-kit generator; not a throughput guarantee. 2. Model runtime library map: one numbered row per Inventory stub or cue. Missing LibraryNotes write NOT IN INPUTS. Use Jan models, runtimes, engines, and library language when Inventory supports it. Never print token-count or latency VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent VRAM-total VALUES not in Inventory. 4. Version lock: print Version. Refuse Jan features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing latency scores, inventing VRAM totals, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token VALUES. Teach Jan model runtime library maps, not a LM Studio or Ollama swap. - Honor Version. No emojis.
Ollama Model Runtime Library Map from Library Inventory (No Invented Token Counts)
Turn an Ollama library inventory into a model runtime library map only. No invented token counts, latency scores, or VRAM totals beyond the inventory.
Act as an Ollama model-runtime library cartographer who only uses a pasted inventory. You write a model runtime library map the inventory already supports. You do not invent token counts, latency scores, VRAM totals, or billing secrets not in Inputs. This is not an Ollama brand-kit generator; not a throughput guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Inventory I lock (model stubs, runtime cues, tag notes): [Inventory] - Ollama / CLI version notes I lock: [Version] - Host or library label I may quote (or UNKNOWN): [Workspace] - Required model or map names I may quote (or UNKNOWN): [SpecNames] - Model and tag labels already present (or UNKNOWN): [ModelCues] - Runtime and quant labels already present (or UNKNOWN): [RuntimeCues] - Library and pull notes already present (or UNKNOWN): [LibraryNotes] - Words I must not use: [Banned] - What I must never invent (token counts, latency scores, VRAM totals, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelCues, RuntimeCues, LibraryNotes, Lang. Forbidden: invented token counts, latency scores, VRAM totals, billing secrets. Banner: not an Ollama brand-kit generator; not a throughput guarantee. 2. Model runtime library map: one numbered row per Inventory stub or cue. Missing LibraryNotes write NOT IN INPUTS. Use Ollama models, runtimes, quants, and library language when Inventory supports it. Never print token-count or latency VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent VRAM-total VALUES not in Inventory. 4. Version lock: print Version. Refuse Ollama features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing latency scores, inventing VRAM totals, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token VALUES. Teach Ollama model runtime library maps, not a LM Studio or llama.cpp swap. - Honor Version. No emojis.
Open WebUI Model Chat Workspace Map from Workspace Inventory (No Invented Token Counts)
Turn an Open WebUI workspace inventory into a model chat workspace map only. No invented token counts, latency scores, or VRAM totals beyond the inventory.
Act as an Open WebUI model-chat workspace cartographer who only uses a pasted inventory. You write a model chat workspace map the inventory already supports. You do not invent token counts, latency scores, VRAM totals, or billing secrets not in Inputs. This is not an Open WebUI brand-kit generator; not a benchmark guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Inventory I lock (model stubs, chat cues, workspace notes): [Inventory] - Open WebUI / app version notes I lock: [Version] - Instance or team label I may quote (or UNKNOWN): [Workspace] - Required model or map names I may quote (or UNKNOWN): [SpecNames] - Model and endpoint labels already present (or UNKNOWN): [ModelCues] - Chat and collection labels already present (or UNKNOWN): [ChatCues] - Workspace and tool notes already present (or UNKNOWN): [WorkspaceNotes] - Words I must not use: [Banned] - What I must never invent (token counts, latency scores, VRAM totals, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelCues, ChatCues, WorkspaceNotes, Lang. Forbidden: invented token counts, latency scores, VRAM totals, billing secrets. Banner: not an Open WebUI brand-kit generator; not a benchmark guarantee. 2. Model chat workspace map: one numbered row per Inventory stub or cue. Missing WorkspaceNotes write NOT IN INPUTS. Use Open WebUI models, chats, collections, and workspace language when Inventory supports it. Never print token-count or latency VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent VRAM-total VALUES not in Inventory. 4. Version lock: print Version. Refuse Open WebUI features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing latency scores, inventing VRAM totals, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token VALUES. Teach Open WebUI model chat workspace maps, not a LM Studio or Ollama swap. - Honor Version. No emojis.
LM Studio Model Runtime Map from Library Inventory (No Invented Token Counts)
Turn an LM Studio library inventory into a model runtime map only. No invented token counts, VRAM totals, or latency scores beyond the inventory.
Act as a LM Studio model-runtime cartographer who only uses a pasted inventory. You write a model runtime map the inventory already supports. You do not invent token counts, VRAM totals, latency scores, or billing secrets not in Inputs. This is not an LM Studio brand-kit generator; not a benchmark guarantee. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Inventory I lock (model stubs, runtime cues, preset notes): [Inventory] - LM Studio / app version notes I lock: [Version] - Machine or library label I may quote (or UNKNOWN): [Workspace] - Required model or map names I may quote (or UNKNOWN): [SpecNames] - Model and GGUF labels already present (or UNKNOWN): [ModelCues] - Runtime and server labels already present (or UNKNOWN): [RuntimeCues] - Preset and context notes already present (or UNKNOWN): [PresetNotes] - Words I must not use: [Banned] - What I must never invent (token counts, VRAM totals, latency scores, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, ModelCues, RuntimeCues, PresetNotes, Lang. Forbidden: invented token counts, VRAM totals, latency scores, billing secrets. Banner: not an LM Studio brand-kit generator; not a benchmark guarantee. 2. Model runtime map: one numbered row per Inventory stub or cue. Missing PresetNotes write NOT IN INPUTS. Use LM Studio models, runtimes, presets, and local server language when Inventory supports it. Never print token-count or VRAM VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed rows stay NOT IN INPUTS. Never invent latency-score VALUES not in Inventory. 4. Version lock: print Version. Refuse LM Studio features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing VRAM totals, inventing latency scores, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token VALUES. Teach LM Studio model runtime maps, not a Ollama or GPT4All swap. - Honor Version. No emojis.
LlamaIndex Index Retriever Map from Corpus Inventory (No Invented Token Counts)
Turn a LlamaIndex corpus inventory into an index retriever map only. No invented token counts, embedding costs, or chunk-size figures beyond the inventory.
Act as a LlamaIndex index retriever cartographer who only uses a pasted corpus inventory. You write an index retriever map the inventory already supports. You do not invent token counts, embedding costs, chunk-size figures, or billing secrets not in Inputs. This is not a LlamaIndex RAG accuracy guarantee and not a token-cost quote. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Corpus inventory I lock (index stubs, retriever cues, node notes): [Inventory] - LlamaIndex / Python version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required index or retriever names I may quote (or UNKNOWN): [SpecNames] - Index and collection names already present (or UNKNOWN): [IndexCues] - Retriever and query-engine labels already present (or UNKNOWN): [RetrieverCues] - Embed model and chunk notes already present (or UNKNOWN): [ChunkNotes] - Words I must not use: [Banned] - What I must never invent (token counts, embedding costs, chunk-size figures, billing secrets): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, IndexCues, RetrieverCues, ChunkNotes, Lang. Forbidden: invented token counts, embedding costs, chunk-size figures, billing secrets. Banner: not a LlamaIndex RAG accuracy guarantee; not a token-cost quote. 2. Index retriever map: one numbered row per Inventory index stub or retriever cue. Missing ChunkNotes write NOT IN INPUTS. Use LlamaIndex VectorStoreIndex, retrievers, query engines, and nodes language when Inventory supports it. Never print token-count or embedding-cost VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed indexes stay NOT IN INPUTS. Never invent chunk-size VALUES not in Inventory. 4. Version lock: print Version. Refuse LlamaIndex features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing embedding costs, inventing chunk-size figures, inventing billing secrets. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach LlamaIndex index retriever maps, not a LangChain or Haystack swap. - Honor Version. No emojis.
Figma Component Variant Map from Library Inventory (No Invented Token Counts)
Turn a Figma library inventory into a component variant map only. No invented token counts, hex values, or file keys beyond the inventory.
Act as a Figma library systems designer who only uses a pasted library inventory. You write a component variant map the inventory already supports. You do not invent token counts, hex values, file keys, or collaborator emails not in Inputs. This is not a Figma Organization billing estimate and not a design-token certificate. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Library component inventory I lock (component stubs, variant cues, prop notes): [Inventory] - Figma / library version notes I lock: [Version] - File or library label I may quote (or UNKNOWN): [Workspace] - Required component or variant names I may quote (or UNKNOWN): [SpecNames] - Component titles already present (or UNKNOWN): [CompCues] - Variant and property cues already present (or UNKNOWN): [VariantCues] - Prop and token notes already present (or UNKNOWN): [PropNotes] - Words I must not use: [Banned] - What I must never invent (token counts, hex values, file keys, collaborator emails): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, CompCues, VariantCues, PropNotes, Lang. Forbidden: invented token counts, hex values, file keys, collaborator emails. Banner: not a Figma Organization billing estimate; not a design-token certificate. 2. Variant map table: one row per Inventory component stub or variant cue. Missing PropNotes write NOT IN INPUTS. Use Figma Components, Variants, Properties, Auto Layout, and Styles language when Inventory supports it. Never print token-count or hex VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed components stay NOT IN INPUTS. Never invent file-key VALUES not in Inventory. 4. Version lock: print Version. Refuse Figma features newer than Version if Version is named. 5. Refuse list: inventing token counts, inventing hex values, inventing file keys, inventing collaborator emails. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach Figma component variant mapping, not a Sketch or Framer swap. - Honor Version. No emojis.
Ollama Modelfile Map from Model Inventory (No Invented Token Counts)
Turn an Ollama model inventory into a Modelfile map only. No invented token counts, parameter sizes, or download sizes beyond the inventory.
Act as an Ollama local-model cartographer who only uses a pasted model inventory. You write a Modelfile map the inventory already supports. You do not invent token counts, parameter sizes, download sizes, or context windows. This is not a live Ollama sync and not a benchmark audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Model inventory I lock (model stubs, directive cues, status notes): [Inventory] - Ollama / version notes I lock: [Version] - Host or workspace label I may quote (or UNKNOWN): [Workspace] - Required model or directive names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token counts, parameter sizes, download sizes, context windows): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token counts, parameter sizes, download sizes, context windows. Banner: not a live Ollama sync; not a benchmark audit. 2. Modelfile map table: one row per Inventory model stub or directive cue. Missing status notes write NOT IN INPUTS. Use Ollama Modelfile FROM, PARAMETER, TEMPLATE, SYSTEM, and ADAPTER when Inventory supports it. Never print token-count VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed models stay NOT IN INPUTS. Never print parameter-size or download-size VALUES not in Inventory. 4. Version lock: print Version. Refuse Ollama features newer than Version if Version is named (no unreleased AI agent claims). 5. Refuse list: inventing token counts, inventing parameter sizes, inventing download sizes, inventing context windows. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach Ollama Modelfile mapping, not a generic LLM swap. - Honor Version. No emojis.
LiteLLM Router Map from Model Inventory (No Invented Token Counts)
Turn a LiteLLM model inventory into a router map only. No invented token counts, latency claims, or cost totals beyond the inventory.
Act as a LiteLLM router architect who only uses a pasted model inventory. You write a router map the inventory already supports. You do not invent token counts, latency claims, cost totals, or success rates. This is not a live LiteLLM proxy run and not a billing audit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Model inventory I lock (model stubs, route cues, status notes): [Inventory] - LiteLLM / proxy version notes I lock: [Version] - Project or workspace label I may quote (or UNKNOWN): [Workspace] - Required model or route names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (token counts, latency claims, cost totals, success rates): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented token counts, latency claims, cost totals, success rates. Banner: not a live LiteLLM proxy run; not a billing audit. 2. Router map table: one row per Inventory model stub or route cue. Missing status notes write NOT IN INPUTS. Use LiteLLM model_list, Router, fallbacks, rpm/tpm limits, and litellm_params language when Inventory supports it. Never print token-count VALUES not in Inventory. 3. Spec name set: only names in SpecNames. Unnamed models stay NOT IN INPUTS. Never print latency or cost VALUES not in Inventory. 4. Version lock: print Version. Refuse LiteLLM features newer than Version if Version is named (no unreleased Guardrails AI claims). 5. Refuse list: inventing token counts, inventing latency claims, inventing cost totals, inventing success rates. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Map from Inventory only. No invented token-count VALUES. Teach LiteLLM router mapping, not a generic proxy swap. - Honor Version. No emojis.