Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / mosaicml/llm-foundry issues and pull requests
#127 - The error of test the Dataloader
Issue -
State: closed - Opened by sysusicily over 1 year ago
- 3 comments
#126 - How to choose a Chinese tokenizer?
Issue -
State: open - Opened by sysusicily over 1 year ago
#125 - How to use composer to train mpt-7b on a single gpu?
Issue -
State: closed - Opened by LisaWang0306 over 1 year ago
- 3 comments
#124 - Finetuning with llm-foundry (composer format)
Issue -
State: open - Opened by xgal over 1 year ago
- 1 comment
#123 - MPT-7b models take very long to load (before actual model is loaded)
Issue -
State: open - Opened by SinanAkkoyun over 1 year ago
#122 - How to install MPT-7B?
Issue -
State: closed - Opened by SinanAkkoyun over 1 year ago
- 10 comments
#121 - Fix licensing typo & context window typo
Pull Request -
State: closed - Opened by brianjking over 1 year ago
- 1 comment
#120 - MPT-7B Finetuning Jupyter notebook request
Issue -
State: closed - Opened by GeorvityLabs over 1 year ago
- 7 comments
#119 - Crash in hf_chat.py after lots of activity with longer output
Issue -
State: closed - Opened by patrickhwood over 1 year ago
- 4 comments
#118 - Set pad_token_id to tokenizer.pad_token_id if not set on command line
Pull Request -
State: open - Opened by patrickhwood over 1 year ago
#117 - GPU memory issue
Issue -
State: open - Opened by zhranj over 1 year ago
- 3 comments
#116 - Add features to hf_generate
Pull Request -
State: closed - Opened by alextrott16 over 1 year ago
#115 - larger scale of mpt
Issue -
State: closed - Opened by WangJW424 over 1 year ago
- 2 comments
#114 - how to run in v100 GPU
Issue -
State: open - Opened by sysusicily over 1 year ago
- 5 comments
#113 - fatal error: cuda.h: No such file or directory
Issue -
State: open - Opened by Babramson over 1 year ago
- 1 comment
#112 - does the non commercial license of the Chat model come from the dataset used to finetune?
Issue -
State: closed - Opened by vince62s over 1 year ago
- 1 comment
#111 - What are the hardware requirements?
Issue -
State: closed - Opened by soloist-tech over 1 year ago
- 1 comment
#110 - Add minimum `mosaicml-streaming` version
Pull Request -
State: closed - Opened by hanlint over 1 year ago
#109 - Precision.AMP_BF16 is not supported for CPU training
Issue -
State: closed - Opened by wj210 over 1 year ago
- 2 comments
#108 - How to fine-tune instruct mpt-7b model?
Issue -
State: open - Opened by dydx-git over 1 year ago
- 6 comments
#107 - the problem about mosaicml-streaming
Issue -
State: closed - Opened by sysusicily over 1 year ago
- 1 comment
#106 - the problem about mosaicml-streaming
Issue -
State: closed - Opened by sysusicily over 1 year ago
- 1 comment
#105 - Generate shorter sentences
Issue -
State: closed - Opened by NarenZen over 1 year ago
- 1 comment
#104 - Question about the "streaming" package
Issue -
State: closed - Opened by LisaWang0306 over 1 year ago
- 1 comment
#103 - Consider using PyTorch 2.0 version of FlashAttention (remove dependency on flash-attn)
Issue -
State: closed - Opened by Sciumo over 1 year ago
- 2 comments
#102 - Update dataloader.py
Pull Request -
State: closed - Opened by nelsontkq over 1 year ago
#101 - Make mpt7b finetuning more obvious
Pull Request -
State: closed - Opened by samhavens over 1 year ago
- 1 comment
#100 - Error in FSDP with composer
Issue -
State: closed - Opened by bjoernpl over 1 year ago
- 3 comments
#99 - Protobuf version conflict
Issue -
State: closed - Opened by junaidid over 1 year ago
- 1 comment
#98 - Add slack and license buttons to readme
Pull Request -
State: closed - Opened by growlix over 1 year ago
#97 - Disable image for pypi
Pull Request -
State: closed - Opened by mvpatel2000 over 1 year ago
#96 - FasterTransformer inference with MPT-7b
Issue -
State: closed - Opened by SinanAkkoyun over 1 year ago
- 4 comments
#95 - How to install torch 1.13.1+cu117?
Issue -
State: closed - Opened by ighodgao over 1 year ago
- 4 comments
#94 - Finetune MPT models with local dataset
Issue -
State: closed - Opened by arpitkk over 1 year ago
- 15 comments
#93 - Finetune MPT-7B with 48GiB of VRAM?
Issue -
State: closed - Opened by juanps90 over 1 year ago
- 1 comment
#92 - getting messy response (response includes #'s)
Issue -
State: closed - Opened by NarenZen over 1 year ago
#91 - How to use the train.py finetuning the pre-trained MPT-7B?
Issue -
State: open - Opened by metacarbon over 1 year ago
- 1 comment
#90 - hf dict cfg overrides
Pull Request -
State: closed - Opened by vchiley over 1 year ago
- 1 comment
#89 - TypeError: Object of type DictConfig is not JSON serializable for HFCausalLM
Issue -
State: closed - Opened by zanussbaum over 1 year ago
- 2 comments
#88 - Evaluation result mismatch
Issue -
State: closed - Opened by congyingxia over 1 year ago
- 9 comments
#87 - Fix sed command for xentropy
Pull Request -
State: closed - Opened by mvpatel2000 over 1 year ago
#86 - Remove xentropy from pypi
Pull Request -
State: closed - Opened by mvpatel2000 over 1 year ago
#85 - Updates to prefixlm and t5
Pull Request -
State: closed - Opened by alextrott16 over 1 year ago
- 2 comments
#84 - Bump composer version
Pull Request -
State: closed - Opened by vchiley over 1 year ago
#83 - HF Auth Token issue
Issue -
State: closed - Opened by ighodgao over 1 year ago
- 4 comments
#82 - Broken on docker image?
Issue -
State: closed - Opened by tginart over 1 year ago
- 14 comments
#81 - Installation issue
Issue -
State: closed - Opened by ighodgao over 1 year ago
- 4 comments
#80 - Fix pypi
Pull Request -
State: closed - Opened by mvpatel2000 over 1 year ago
#79 - URL not found
Issue -
State: closed - Opened by dariocazzani over 1 year ago
- 4 comments
#78 - Error in Triton implementation
Issue -
State: closed - Opened by NarenZen over 1 year ago
- 1 comment
#77 - Error in triton implementation
Issue -
State: closed - Opened by NarenZen over 1 year ago
#76 - Error in triton implementation
Issue -
State: closed - Opened by NarenZen over 1 year ago
#75 - does it work on local machine or someone with limited resources
Issue -
State: closed - Opened by rabsher over 1 year ago
- 6 comments
#74 - Remove todo in workflow
Pull Request -
State: closed - Opened by mvpatel2000 over 1 year ago
#73 - Update version
Pull Request -
State: closed - Opened by dakinggg over 1 year ago
#72 - Update README.md
Pull Request -
State: closed - Opened by ejyuen over 1 year ago
#71 - Windows support ?
Issue -
State: closed - Opened by deepbeepmeep over 1 year ago
- 7 comments
#70 - Configs say optimizer is AdamW but blog post says the optimizer is LION
Issue -
State: closed - Opened by Craigacp over 1 year ago
- 3 comments
#69 - Add venv instructions to readme
Pull Request -
State: closed - Opened by dakinggg over 1 year ago
#68 - Finetuning
Issue -
State: closed - Opened by canamika27 over 1 year ago
- 7 comments
#67 - FasterTransformer
Issue -
State: closed - Opened by xgal over 1 year ago
- 34 comments
#66 - multilingual ability
Issue -
State: closed - Opened by yangjianxin1 over 1 year ago
- 10 comments
#65 - This project does not rely on DeepSpeed and Megatron?
Issue -
State: closed - Opened by lc222 over 1 year ago
- 1 comment
Labels: good first issue
#64 - Not an issue, a question - Peft/LoRa finetuning a possibility?
Issue -
State: open - Opened by jamesd256 over 1 year ago
- 11 comments
#63 - Issues following instructions on Ubuntu 22.04
Issue -
State: closed - Opened by jamesd256 over 1 year ago
- 8 comments
#62 - Fused Cross Entropy is not installed. Either (1) have a CUDA-compatible GPU and `pip install .[gpu]`, or (2) set your config model.loss_fn=torch_crossentropy.
Issue -
State: closed - Opened by Stanlito-AI over 1 year ago
- 6 comments
#61 - could you share links to the WandB runs of your trained models?
Issue -
State: closed - Opened by DanqingZ over 1 year ago
- 1 comment
#60 - Add GGML support
Issue -
State: closed - Opened by jploski over 1 year ago
- 5 comments
#59 - Reproduce result of Boolq on LLaMA-7B
Issue -
State: closed - Opened by mx8435 over 1 year ago
- 14 comments
#58 - mismatched config compared with blog
Issue -
State: closed - Opened by donglixp over 1 year ago
- 3 comments
#57 - Can we use PyTorch Version 2 to train models?
Issue -
State: closed - Opened by linhduongtuan over 1 year ago
- 1 comment
#56 - Any plans for 13B+ models?
Issue -
State: closed - Opened by artyemk over 1 year ago
- 2 comments
#55 - Update inference benchmarking script
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
- 1 comment
#54 - getting OOM on 8 nvidia GPUs with 40GB memory each
Issue -
State: closed - Opened by arpitg1991 over 1 year ago
- 13 comments
#53 - Update generation scripts
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#52 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
- 1 comment
#51 - Add links to README
Pull Request -
State: closed - Opened by hanlint over 1 year ago
#50 - Update README.md
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#49 - name -> hf_name
Pull Request -
State: closed - Opened by alextrott16 over 1 year ago
#48 - Update header photo, add `eval.py` to quickstart
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#47 - Adding loss to MPTForCausalLM fwd if labels arg is not None
Pull Request -
State: closed - Opened by vchiley over 1 year ago
- 2 comments
#46 - update readme and updt __init__
Pull Request -
State: closed - Opened by vchiley over 1 year ago
#45 - Update README.md
Pull Request -
State: closed - Opened by growlix over 1 year ago
- 1 comment
#44 - Fix local link in train README
Pull Request -
State: closed - Opened by sashaDoubov over 1 year ago
#43 - Fix broken links in inference README
Pull Request -
State: closed - Opened by sashaDoubov over 1 year ago
#42 - Cleanup README, YAMLs, `hf_generate.py`
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#41 - fix inference scripts and readme
Pull Request -
State: closed - Opened by dakinggg over 1 year ago
#40 - Icl tests
Pull Request -
State: closed - Opened by bmosaicml over 1 year ago
- 2 comments
#39 - Fix Llama spelling
Pull Request -
State: closed - Opened by bcui19 over 1 year ago
#38 - Fix PIQA continuation_delimiters
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#35 - gate warning with verbose flag
Pull Request -
State: closed - Opened by vchiley over 1 year ago
#33 - HF, JSON, and CSV dataset prep
Pull Request -
State: closed - Opened by codestar12 over 1 year ago
- 1 comment
#32 - Add LLaMa and MPT HFCausalLM support
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#25 - mv cfg defaults
Pull Request -
State: closed - Opened by vchiley over 1 year ago
#23 - convert examples v004 state dict to llm-foundry state dict
Pull Request -
State: closed - Opened by vchiley over 1 year ago
- 2 comments
#16 - Improve HF model loading behavior
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#14 - inference instructor example
Pull Request -
State: closed - Opened by RR4787 over 1 year ago
- 1 comment
#13 - Make ICL configurations more concise
Pull Request -
State: closed - Opened by abhi-mosaic over 1 year ago
#12 - updt model config; add attn config
Pull Request -
State: closed - Opened by vchiley over 1 year ago
#11 - Update README.md
Pull Request -
State: closed - Opened by jacobfulano over 1 year ago