starcoder2
starcoder2 copied to clipboard
Home of StarCoder2!
model.save_pretrained saves only the model but not the trained adapters.
A year ago, the raw Megatron weights for StarCoder [were released](https://github.com/bigcode-project/starcoder/issues/25). Would it be possible to release the Megatron weights for StarCoder2, especially the 15B variant? Also, publishing a script...
from fim paper (https://arxiv.org/pdf/2207.14255.pdf) section 3.1: SPM mode can be used to reuse kv cache across completion requests. SPM modes can enable further latency optimization (which is very important in...
I am new to starcode. when I run the follow demo: ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM checkpoint = "./starcoder2-3b" tokenizer = AutoTokenizer.from_pretrained(checkpoint) model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)...
Does this support fill-in-the-middle completion?
Hi, currently I'm researching the impact of different retrieval-augmented generation (RAG) techniques on the LLM effect. We are attempting to replicate the CrossCodeEval from the "StarCoder 2 and The Stack...
Hi there, I hope this message finds you well. I am currently exploring the process of fine-tuning models using my own codebase, and I was hoping to seek some guidance...
Is there any progress on the future work on the research project? Want to know whether has chance to participate in the future work. Or do we have any community...
I loaded startcoder2 in llmstudio and asked it to write a python script that solves the Fibonacci series, but it outputs a bunch of weird results.  
wtf?
``` C:\Users\reinz>ollama run starcoder2:7b >>> thistuple = ("apple", "banana", "cherry") ... print(thistuple) ... >>> ? why dont you generate text ! ? because I can't. ? what do you mean?...