Comments (4)
In what scenario are you getting -inf as the top logprob? That's really weird
from aphrodite-engine.
I was sending logit_bias
and thought it might be the issue, but I removed it and the error persists
{'301': 100.0, '528': 100.0, '626': 100.0, '766': 100.0, '885': 100.0, '1153': 100.0, '1424': 100.0, '1472': 100.0, '1999': 100.0, '4966': 100.0, '9613': 100.0, '9796': 100.0, '11158': 100.0, '12327': 100.0, '12758': 100.0, '14610': 100.0, '15377': 100.0, '18782': 100.0, '19253': 100.0, '21104': 100.0, '21620': 100.0, '22314': 100.0, '23407': 100.0, '23451': 100.0, '24173': 100.0, '25945': 100.0, '26230': 100.0, '27719': 100.0}
These are my SampingParams:
SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.17, temperature=1.31, top_p=0.14, top_k=49, top_a=0.52, min_p=0.0, tfs=1.0, eta_cutoff=10.42, epsilon_cutoff=1.49, typical_p=1.0, mirostat_mode=0, mirostat_tau=5.0, mirostat_eta=0.1, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['\n###', '</s>', '<|', '\n#', '\n\n\n'], stop_token_ids=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=1, custom_token_bans=[], logprobs=10, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True)
I'm using TheBloke/MythoMax-L2-Kimiko-v2-13B-GPTQ
for this case
I can debug further until I find why this happens.
from aphrodite-engine.
i get this with miku and tsukasa, mikus hotfix fixed for me
from aphrodite-engine.
Sorry I forgot to get back to you on this. Yes, AFAIK, JSON doesn't support -inf
as a numeric value. If you can open a PR to fix that, it'd be great.
And yes, -inf
value is expected; happens when the probs for a token is effectively zero. The log of zero is -inf
. Your workaround of setting -inf
to -1000
should be fine.
from aphrodite-engine.
Related Issues (20)
- Bad generation with GGUF and OpenAI api HOT 1
- [Bug]: openAI endpoint crashing on "no locator available" HOT 1
- [Bug]: Pydantic serializer issue when pinging /v1/models HOT 2
- [Bug]: `ValueError: Out of range float values are not JSON compliant` when requesting logprobs from awq model HOT 1
- [sparsetral and Qwen2idae]: support for mixtral of lora HOT 12
- [Bug]: exl2 is not auto detected HOT 2
- [Usage]: nccl and cupy problem "no cupy" and "NCCL_ERROR_UNHANDLED_CUDA_ERROR" when use TP in wsl HOT 10
- [Bug]: Issue when trying to load a AWQ model with --load-in-4bits for mixtral flavors HOT 3
- Installation fails on NAVI gpu HOT 2
- [Bug]: loading model with int8 kv cache chokes HOT 1
- [Usage]: Question about VRAM requirement and temperature HOT 2
- [Feature]: Support YiForCausalLM HOT 5
- [Misc]: Building docker container requires insane amount of memory HOT 7
- [Bug]: Outlines json guided decoding HOT 7
- [Feature]: BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences HOT 1
- [Bug]: Does --trust-remote-code work? HOT 1
- [Bug]: multi GPU crashes backend HOT 6
- [Bug]: WSL Cuda out of Memory when Trying to Load GGUF Model HOT 8
- [Usage]: load-in-4bit not load after converted, and it seem not use swap well
- [Bug]: KV Cache and Max Tokens - Lack of Consistency
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from aphrodite-engine.