eleutherai/cookbook issues and pull requests

#47 - add mup guide

Pull Request - State: closed - Opened by Quentin-Anthony about 2 months ago

#47 - add mup guide

Pull Request - State: closed - Opened by Quentin-Anthony about 2 months ago

#46 - Add author name to transformer inference arithmetic

Pull Request - State: closed - Opened by Quentin-Anthony about 2 months ago

#46 - Add author name to transformer inference arithmetic

Pull Request - State: closed - Opened by Quentin-Anthony about 2 months ago

#45 - [Question] Does the model param include the `lm-head`?

Issue - State: closed - Opened by yiliu30 3 months ago - 1 comment

#45 - [Question] Does the model param include the `lm-head`?

Issue - State: closed - Opened by yiliu30 3 months ago - 1 comment

#44 - Calc: more flexible GLU MLP (Llama) arguments

Pull Request - State: closed - Opened by haileyschoelkopf 3 months ago

#44 - Calc: more flexible GLU MLP (Llama) arguments

Pull Request - State: closed - Opened by haileyschoelkopf 3 months ago

#43 - Improve Handling of Llama-style Models

Issue - State: open - Opened by Quentin-Anthony 3 months ago

#43 - Improve Handling of Llama-style Models

Issue - State: open - Opened by Quentin-Anthony 3 months ago

#42 - Improve Quantization

Issue - State: open - Opened by Quentin-Anthony 3 months ago

#42 - Improve Quantization

Issue - State: open - Opened by Quentin-Anthony 3 months ago

#41 - Add tied embeddings and output tokens option

Pull Request - State: closed - Opened by Quentin-Anthony 3 months ago

#41 - Add tied embeddings and output tokens option

Pull Request - State: closed - Opened by Quentin-Anthony 3 months ago

#40 - requirements.txt or versions ?

Issue - State: open - Opened by benihime91 5 months ago

#40 - requirements.txt or versions ?

Issue - State: open - Opened by benihime91 5 months ago

#39 - Add HuggingFace arg so that arch is automatic

Pull Request - State: closed - Opened by bhavnicksm 6 months ago - 11 comments

#39 - Add HuggingFace arg so that arch is automatic

Pull Request - State: closed - Opened by bhavnicksm 6 months ago - 11 comments

#38 - Add option for tied embeddings

Pull Request - State: closed - Opened by Quentin-Anthony 7 months ago

#38 - Add option for tied embeddings

Pull Request - State: closed - Opened by Quentin-Anthony 7 months ago

#37 - Add MLP Linears Argument

Pull Request - State: closed - Opened by Quentin-Anthony 8 months ago

#37 - Add MLP Linears Argument

Pull Request - State: closed - Opened by Quentin-Anthony 8 months ago

#36 - calc_transformer_mem.py is inaccurate for most popular open models

Issue - State: closed - Opened by rationalism 8 months ago - 1 comment

#36 - calc_transformer_mem.py is inaccurate for most popular open models

Issue - State: closed - Opened by rationalism 8 months ago - 1 comment

#35 - Add missing `--ffn-expansion-factor` to FLOPs calculator script

Pull Request - State: closed - Opened by haileyschoelkopf 8 months ago - 2 comments

#35 - Add missing `--ffn-expansion-factor` to FLOPs calculator script

Pull Request - State: closed - Opened by haileyschoelkopf 8 months ago - 2 comments

#34 - benchmark header: add gpu info

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#34 - benchmark header: add gpu info

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#33 - use the best experiment for max tflops #2

Pull Request - State: closed - Opened by stas00 9 months ago

#33 - use the best experiment for max tflops #2

Pull Request - State: closed - Opened by stas00 9 months ago

#32 - use the best experiment for max tflops

Pull Request - State: closed - Opened by stas00 9 months ago

#32 - use the best experiment for max tflops

Pull Request - State: closed - Opened by stas00 9 months ago

#31 - Add simple inference FLOP counter to `calc_transformer_flops.py`

Pull Request - State: closed - Opened by haileyschoelkopf 9 months ago - 6 comments

#31 - Add simple inference FLOP counter to `calc_transformer_flops.py`

Pull Request - State: closed - Opened by haileyschoelkopf 9 months ago - 6 comments

#30 - Automate plotting

Pull Request - State: closed - Opened by stas00 9 months ago

#30 - Automate plotting

Pull Request - State: closed - Opened by stas00 9 months ago

#29 - self-document the benchmark's setup

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#29 - self-document the benchmark's setup

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#28 - [fix] output file breakage

Pull Request - State: closed - Opened by stas00 9 months ago

#28 - [fix] output file breakage

Pull Request - State: closed - Opened by stas00 9 months ago

#27 - quick fix for transformer_flops.py error

Pull Request - State: closed - Opened by jahatef 9 months ago

#27 - quick fix for transformer_flops.py error

Pull Request - State: closed - Opened by jahatef 9 months ago

#26 - [sizing] fixes and enhancements

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#26 - [sizing] fixes and enhancements

Pull Request - State: closed - Opened by stas00 9 months ago - 1 comment

#25 - fix varname bug

Pull Request - State: closed - Opened by Quentin-Anthony 9 months ago

#25 - fix varname bug

Pull Request - State: closed - Opened by Quentin-Anthony 9 months ago

#24 - Add Jacob to authors and update readme

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#24 - Add Jacob to authors and update readme

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#23 - Update README and add Jacob to authors

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#23 - Update README and add Jacob to authors

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#22 - Improve Memory Calculation Script

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#22 - Improve Memory Calculation Script

Pull Request - State: closed - Opened by Quentin-Anthony 10 months ago

#21 - I/O Benchmarking

Issue - State: open - Opened by Quentin-Anthony 10 months ago

#21 - I/O Benchmarking

Issue - State: open - Opened by Quentin-Anthony 10 months ago

#20 - Fix webpage hosting

Issue - State: open - Opened by Quentin-Anthony 11 months ago

#19 - Add Repo Citation

Issue - State: closed - Opened by Quentin-Anthony 11 months ago - 1 comment

#19 - Add Repo Citation

Issue - State: closed - Opened by Quentin-Anthony 11 months ago - 1 comment

#18 - Add communication volume calculation script

Issue - State: open - Opened by Quentin-Anthony 11 months ago

#18 - Add communication volume calculation script

Issue - State: open - Opened by Quentin-Anthony 11 months ago

#17 - Add Inference FLOP Calculation

Issue - State: open - Opened by Quentin-Anthony 11 months ago

#17 - Add Inference FLOP Calculation

Issue - State: open - Opened by Quentin-Anthony 11 months ago

#16 - Benchmarking

Issue - State: closed - Opened by Akash08naik 11 months ago - 1 comment

#16 - Benchmarking

Issue - State: closed - Opened by Akash08naik 11 months ago - 1 comment

#15 - flop calculation

Issue - State: closed - Opened by Akash08naik 11 months ago - 3 comments

#15 - flop calculation

Issue - State: closed - Opened by Akash08naik 11 months ago - 3 comments

#14 - Fix utilities typo in readme

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#14 - Fix utilities typo in readme

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#13 - Set up model-directory site

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#13 - Set up model-directory site

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#12 - Update README and add model directory site

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#12 - Update README and add model directory site

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#11 - Add utilities to README.md

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#11 - Add utilities to README.md

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#10 - Update README.md

Pull Request - State: closed - Opened by StellaAthena 11 months ago - 1 comment

#10 - Update README.md

Pull Request - State: closed - Opened by StellaAthena 11 months ago - 1 comment

#9 - Add HParam spreadsheet

Pull Request - State: closed - Opened by StellaAthena 11 months ago

#9 - Add HParam spreadsheet

Pull Request - State: closed - Opened by StellaAthena 11 months ago

#8 - Update README

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#7 - Miscellaneous Fixes

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#7 - Miscellaneous Fixes

Pull Request - State: closed - Opened by Quentin-Anthony 11 months ago

#6 - Transformer Sizing

Pull Request - State: closed - Opened by jahatef 11 months ago

#6 - Transformer Sizing

Pull Request - State: closed - Opened by jahatef 11 months ago

#5 - Draft: GQA/MQA in calc. scripts

Pull Request - State: closed - Opened by haileyschoelkopf 11 months ago

#4 - Documentation Updates

Pull Request - State: closed - Opened by haileyschoelkopf 11 months ago

#3 - Update README.md

Pull Request - State: closed - Opened by StellaAthena 11 months ago

#2 - Inference FLOPs

Issue - State: closed - Opened by Quentin-Anthony 11 months ago - 2 comments

#1 - Add HuggingFace arg so that arch is automatic

Issue - State: open - Opened by Quentin-Anthony 11 months ago - 3 comments

GitHub / eleutherai/cookbook issues and pull requests