Comments (1)
Hmm "regression" must have happened in our dependency (either transformers
or tokenizers
).
Nothing changed in llama itself, but thereล a codepath which loads LlamaTokenizer
first, and fallsback to AutoTokenizer
(which should be the one to use for codellama).
However, it seems that now LlamaTokenizer
works, but fails to account for the added tokens, and therefore the state of the tokenizer is invalid.
from text-generation-inference.
Related Issues (20)
- API_KEY argument HOT 2
- Fp8 support KV-Cache HOT 1
- HuggingFaceM4/idefics2: TGI would crash when I set do_image_splitting to False
- What is TGI's graceful shutdown behavior? HOT 1
- Cannot load model HuggingFaceM4/idefics2-8b-AWQ HOT 8
- RuntimeError: FlashAttention only supports Ampere GPUs or newer. HOT 12
- GPU memory not saturated using microsoft/Phi-3-small-128k-instruct HOT 1
- Can I run text-generation-interface "offline" HOT 1
- Guide/support for quantization + MLPSpeculator HOT 3
- ROCm: Server error: transport error when running batch size >=2 (Falcon-11B) HOT 2
- ROCm: Support models with head_dim>128
- ROCm: mismatch in generation for gpt2
- Poor/inconsistent results from Phi-3-mini-128k HOT 1
- idefics2: Sizes of tensors must match except in dimension 0. Expected size 448 but got size 447 for tensor number 2 in the list. HOT 2
- Some typo error in the picture of flash_attention.md HOT 2
- Unable to run TGI following the instructions on the readme HOT 5
- docker-compose throws `flash attention is not installed` error HOT 3
- Phi-3-mini-128k crashes on simple query HOT 2
- Add Environment Variable for OTLP Service Name HOT 2
- ImportError: libcuda.so.1: cannot open shared object file: No such file or directory HOT 10
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from text-generation-inference.