mirror of
https://github.com/CherryHQ/cherry-studio.git
synced 2026-01-09 23:10:20 +08:00
43 lines
1.5 KiB
YAML
43 lines
1.5 KiB
YAML
id: arcee-ai/caller-large
|
||
canonical_slug: arcee-ai/caller-large
|
||
hugging_face_id: ''
|
||
name: 'Arcee AI: Caller Large'
|
||
type: chat
|
||
created: 1746487869
|
||
description: 'Caller Large is Arcee''s specialist "function‑calling" SLM built to orchestrate external tools and APIs. Instead of maximizing next‑token accuracy, training focuses on structured JSON outputs, parameter extraction and multi‑step tool chains, making Caller a natural choice for retrieval‑augmented generation, robotic process automation or data‑pull chatbots. It incorporates a routing head that decides when (and how) to invoke a tool versus answering directly, reducing hallucinated calls. The model is already the backbone of Arcee Conductor''s auto‑tool mode, where it parses user intent, emits clean function signatures and hands control back once the tool response is ready. Developers thus gain an OpenAI‑style function‑calling UX without handing requests to a frontier‑scale model. '
|
||
context_length: 32768
|
||
architecture:
|
||
modality: text->text
|
||
input_modalities:
|
||
- text
|
||
output_modalities:
|
||
- text
|
||
tokenizer: Other
|
||
instruct_type: null
|
||
pricing:
|
||
prompt: '0.00000055'
|
||
completion: '0.00000085'
|
||
input_cache_read: ''
|
||
input_cache_write: ''
|
||
request: '0'
|
||
image: '0'
|
||
web_search: '0'
|
||
internal_reasoning: '0'
|
||
unit: 1
|
||
currency: USD
|
||
supported_parameters:
|
||
- tools
|
||
- tool_choice
|
||
- max_tokens
|
||
- temperature
|
||
- top_p
|
||
- stop
|
||
- frequency_penalty
|
||
- presence_penalty
|
||
- top_k
|
||
- repetition_penalty
|
||
- logit_bias
|
||
- min_p
|
||
- response_format
|
||
model_provider: arcee-ai
|