Comments (8)
Wohoo! btw - Just a heads-up the model is a FIM type. So would be a little different in terms of the way you prompt it.
In case you want to see the changes from Mistral to StarCoder2: huggingface/transformers#29120
from mlx-examples.
What's FIM? And does the HF tokenizer template handle that or do we need to do something special?
FIM - Fill in the Middle. Nothing special. Just that it is not chat-tuned.
https://huggingface.co/bigcode/starcoder2-15b#running-the-model-on-cpugpumulti-gpu
from mlx-examples.
FIM: Fill in the Middle arxiv-paper
from mlx-examples.
Happy to accept a contribution for that!
from mlx-examples.
@awni I'll take a stab at it and see what I can do! Could you point me to a good starting point?
from mlx-examples.
@awni Could you also assign me to this issue? I can't seem to do it
from mlx-examples.
Of course!
So it's relatively simple, you add the model file to this directory: https://github.com/ml-explore/mlx-examples/tree/main/llms/mlx_lm/models
You can see other examples in there, I recommend starting from one of the models that is pretty similar to starcoder2
Make sure the name of the model file is the same as the model_type
in the config (starcoder2
) (https://huggingface.co/bigcode/starcoder2-7b/blob/main/config.json#L17)
If you want to add LoRA support you can edit this section of the code as needed
from mlx-examples.
Just a heads-up the model is a FIM type
What's FIM? And does the HF tokenizer template handle that or do we need to do something special?
from mlx-examples.
Related Issues (20)
- Llama-3-8B-Instruct-Gradient-1048k-4bit not working? HOT 2
- Generating after LORA training CAN NOT Stop Properly HOT 3
- Issue with Fusing Models - Output is Bad HOT 2
- GatedRepoError: 401 Client Error; "You must be authenticated to access it." HOT 1
- [Feature Request] When generating using mlx_lm, specify data format HOT 2
- how to merge lora adapter to base model HOT 1
- delete and uninstall HOT 11
- KV Cache can only process more than self.step tokens if offset % step == 0 HOT 2
- Text to Speech MLX model. HOT 1
- SLM Example Code HOT 1
- Enhance load function to support model configuration editing HOT 1
- Support for full set of output formats - e.g. vtt, json and json-full HOT 2
- Whisper stutters HOT 8
- mlx 0.13 very slow with q8 and fp16 HOT 5
- Fine tuned a Mixtral-8x7B-Instruct-v0.1 model and unable to load with AutoModelForCausalLM HOT 1
- Phi-3-mini-4k-instruct : Failing to stop at <|end|> on generating the answer. HOT 5
- PaliGemma 4bit Quantization broken and Inference issues. HOT 27
- [Feature Request] Function Calling for mlx_lm.server HOT 4
- OS system requirement for mlx HOT 1
- 01-ai/Yi-1.5-9B-Chat got ValueError: Cannot instantiate this tokenizer from a slow version. HOT 4
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 mlx-examples.