CodeTF

CodeTF copied to clipboard

Unable to run example humaneval code

4

`!pip install sentencepiece from codetf.models import load_model_pipeline from codetf.data_utility.human_eval_dataset import HumanEvalDataset from codetf.performance.model_evaluator import ModelEvaluator import os os.environ["HF_ALLOW_CODE_EVAL"] = "1" os.environ["TOKENIZERS_PARALLELISM"] = "true" model_class = load_model_pipeline(model_name="causallm", task="pretrained", model_type="codegen-350M-mono", is_eval=True, load_in_8bit=True,...

yaoyanglee

I tried to run the demo example for fine tuning the CodeT5+ Model in the README with the peft changed to `prefixtuning` ```python from codetf.trainer.codet5_trainer import CodeT5Seq2SeqTrainer from codetf.data_utility.codexglue_dataset import...

Paul-B98

I'm interested in performing embeddings of source code files for measuring the semantic similarity of content, but I'm not sure which model and task are better suited for my case...

SasCezar

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.63.0 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...

dependabot[bot]

Bumps [transformers](https://github.com/huggingface/transformers) from 4.30.2 to 4.38.0. Release notes Sourced from transformers's releases. v4.38: Gemma, Depth Anything, Stable LM; Static Cache, HF Quantizer, AQLM New model additions 💎 Gemma 💎 Gemma...

dependabot[bot]

I tried the code from [`test_codet5_multitask.py`](https://github.com/salesforce/CodeTF/blob/main/test_inference/test_codet5_multitask.py) and for both `translated_code_snippets` and `summaries`, I get the Python code translated into Java.

michaelmior

Hi! I am tring using `CodeXGLUE refinement dataset`, but I encounter error below: ```python Traceback (most recent call last): File "/Users/zhengyi/Desktop/code/python/llm-projects/CodeT5-fine-tune/lora.py", line 37, in main() File "/Users/zhengyi/Desktop/code/python/llm-projects/CodeT5-fine-tune/lora.py", line 17, in...

Martin7-1

Support new models

1

Hi, Is it possible to have the library dynamically support other models such as GraphCodeBERT, and PLBART? Thanks.

FahadEbrahim

I want to fine tuning codetf to generate json rule code.

1

How can I customize my dataset? this is the snippet of json. { "type": "page", "body": { "type": "collapse-group", "activeKey": [ "1" ], "body": [ { "type": "collapse", "key": "1",...

CharellKing

MPS support

1

It would be nice to support Metal Performance Shaders backend for pytorch on macOS the main changes for inference seem to be: - `load_in_8bit` must be `False` - `device_map` set...

tmm1