MCPcopy Index your code
hub / github.com/abetlen/llama-cpp-python / create_completion

Function create_completion

llama_cpp/llama_chat_format.py:2108–2134  ·  view source on GitHub ↗
(prompt, stop, grammar)

Source from the content-addressed store, hash-verified

2106 return grammar
2107
2108 def create_completion(prompt, stop, grammar):
2109 completion = cast(
2110 llama_types.Completion,
2111 llama.create_completion(
2112 prompt=prompt,
2113 temperature=temperature,
2114 top_p=top_p,
2115 top_k=top_k,
2116 min_p=min_p,
2117 typical_p=typical_p,
2118 stream=stream,
2119 stop=stop,
2120 max_tokens=max_tokens,
2121 presence_penalty=presence_penalty,
2122 frequency_penalty=frequency_penalty,
2123 repeat_penalty=repeat_penalty,
2124 tfs_z=tfs_z,
2125 mirostat_mode=mirostat_mode,
2126 mirostat_tau=mirostat_tau,
2127 mirostat_eta=mirostat_eta,
2128 model=model,
2129 logits_processor=logits_processor,
2130 grammar=grammar,
2131 ),
2132 )
2133
2134 return completion
2135
2136 content = ""
2137 function_calls, function_bodies = [], []

Callers 2

generate_streamingFunction · 0.70

Calls 1

create_completionMethod · 0.80

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…