Comments (4)
@lapp0 Oops apologies I didn't reply - I made CodeLlama-34b
work, and it has a RoPE scaling factor of 1000000. So Yi-34B with the extra RoPE Scaling should work fine!!
from unsloth.
@lapp0 Yes technically RoPE scaling was just added as a preliminary support.
You can either change max_seq_length
to whatever number you desire, and I will handle RoPE scaling internally.
Or you can add a RoPE scaling dictionary yourself.
This is all preliminary support though
from unsloth.
Does unsloth currently implement the expected behavior of rope theta being set by the base models config.json
on hf?
e.g. https://huggingface.co/chargoddard/Yi-34B-Llama/blob/main/config.json#L18
Or are there any issues I might run into which I should be aware of when dealing with long context base models?
from unsloth.
@lapp0 I'm not 100% sure - I think it'll use the internal rope theta / scaling if you don't touch rope_scaling
as the parameter. I'll have to get back to you
from unsloth.
Related Issues (20)
- AutoModelForSequenceClassification or output is only one token HOT 3
- Question: Regarding the unsloth Trainer ! HOT 5
- Model inference - performace drop when using unsloth HOT 1
- Llama3+Unsloth+PEFT with batched inference, and apply_chat_template results in infinite eot_id HOT 2
- Support for model trained by OLMo? HOT 1
- Is fast rope exactly equivalent to llama's apply_rotary_pos_emb? HOT 2
- Support for FP8 quantization HOT 1
- ModuleNotFoundError: No module named 'torch.nn.attention' HOT 2
- Using dtype=Bfloat16 on colab L4 instances fails HOT 2
- Support for Mistral Nemo 2407 HOT 5
- Gemma2 fails saving as GGUF HOT 1
- Out of memory error while finetuning unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit HOT 3
- How to load the fine-tuned lora adapter and the downloaded model from the local directory for inference? HOT 1
- Mistral 12b Nemo Error: Model_kwargs not used ['token_type_ids'] HOT 4
- Error in tutorial notebook LLama3-8b HOT 2
- Size Mismatch Issue
- Llama-2 models: ValueError: Duplicated key name 'tokenizer.chat_template' HOT 2
- Utilizing Intel GPU for Fine-tuning LLMs
- Error when deploying on HF inference endpoints
- The merged model has no inference process
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 unsloth.