Comments (3)
Oh. It seems like you mean the single file you'd get from running llama.donwload
from pyllama. Let me try it out...
from nebuly.
Hi @StrangeTcy, thanks for reaching out.
The first time that the model is loaded, you probably won't have the checkpoints dir in /models.
The folder is created when during training checkpoints are saved and the folder gets populated.
To specify the models from HF you just need to type in the config.yaml in the model field the name of the model from HF that is passed to transformer.AutoModel() when instantiating the model.
Be aware that HF itself had an issue when loading the tokenizer for llama. You may need to check that if it is still an issue.
from nebuly.
The first time the model is loaded from ./models
, there are indeed no checkpoints there, but they can be downloaded with the python or bash script from pyllama.
As for HF models and LLaMA, HF transformers are indeed handled by the
self.model = AutoModelForCausalLM.from_pretrained(
config.model,
)
``` in the `actor.py`, but pure llama models go through `load_model` from `llama_model.py`.
I guess I should try something like `decapoda-research/llama-7b-hf` as an HF model instead of the single-file llama checkpoint
from nebuly.
Related Issues (20)
- [chatllama]Do I need to split the llama model manully? HOT 2
- [Chatllama] facebook/opt-350m is missing in rlhf/model_list.py HOT 2
- module not found:chatllama.rlhf.dataset HOT 1
- Support for torch 2.0 HOT 1
- Issues with accelerate and deepspeed training HOT 4
- [chatllama]How models enable inference HOT 1
- [chatllama]Puzzled about the update of the critic model
- [Speedster] Optimization failed with PytorchBackendCompiler HOT 4
- yolov8 + nebuly | AttributeError: type object 'DummyClass' has no attribute 'models' HOT 10
- Evaluating accuracy of only the reward model
- [speedster] _dl_check_map_versions assertion error with optimize_model and ONNX compilers HOT 3
- torch2.0 support on speedster HOT 2
- Yolov8-Pose Model
- [ Speedster] With Hugging Face notebook code on nebulydocker/nebullvm container: RuntimeError: Expected all tensors to be on the same device HOT 5
- How to generate and perform inference for an ONNX model HOT 2
- Forward Forward Algorithm Questions HOT 2
- [Speedster] TensorRt OSError: [WinError 127] The specified procedure could not be found
- [Speedster] optimize_model took 10 hours, and it's not over yet
- nebullvm LICENSE and commercial use?
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 nebuly.