scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

Merge pull request #3170 from rick-github/ollama-special-symbol

Browse source 
Disable special tokens in ollama completion when counting tokens
This commit is contained in:
Krish Dholakia 2024-04-20 11:57:01 -07:00 • committed by GitHub
commit 78579d4a24
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/ollama.py
View file

@ -228,7 +228,7 @@ def get_ollama_response(
model_response["choices"][0]["message"]["content"] = response_json["response"]
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + model
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt))) # type: ignore
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(prompt, disallowed_special=()))) # type: ignore
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,
@ -330,7 +330,7 @@ async def ollama_acompletion(url, data, model_response, encoding, logging_obj):
]
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + data["model"]
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(data["prompt"]))) # type: ignore
prompt_tokens = response_json.get("prompt_eval_count", len(encoding.encode(data["prompt"], disallowed_special=()))) # type: ignore
completion_tokens = response_json.get("eval_count", len(response_json.get("message",dict()).get("content", "")))
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,