deepseek-ai/ESFT
1
0
Fork 0
mirror of https://github.com/deepseek-ai/ESFT.git synced 2026-11-05 00:57:35 +00:00
Code Issues 7 Projects Packages Wiki Activity

[PR #3] [CLOSED] Add training code and multi-gpu eval code #20

New issue
Closed
opened 2026-10-26 21:06:50 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-26 21:06:50 +00:00
Owner
Copy link

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/ESFT/pull/3
Author: @ZihanWang314
Created: 8/10/2024
Status: ❌ Closed

Base: main ← Head: main

📝 Commits (2)

📊 Changes

19 files changed (+2864 additions, -158 deletions)

View changed files

➕ .gitignore (+1 -0)
📝 README.md (+42 -17)
➕ configs/base.yaml (+31 -0)
➕ deepseek/__init__.py (+0 -0)
➕ deepseek/configuration_deepseek.py (+206 -0)
➕ deepseek/modeling_deepseek.py (+1918 -0)
📝 esft.py (+25 -8)
➕ eval_multigpu.py (+92 -0)
📝 scripts/eval.sh (+15 -3)
📝 scripts/eval_expert.sh (+7 -5)
➕ scripts/expert/generate_expert_config.py (+97 -0)
➕ scripts/expert/get_expert_scores.py (+78 -0)
➖ scripts/generate_expert_config.py (+0 -50)
➖ scripts/get_expert_scores.py (+0 -75)
➕ scripts/train.sh (+12 -0)
➕ scripts/train_ep.sh (+11 -0)
➕ train.py (+117 -0)
➕ train_ep.py (+154 -0)
📝 utils.py (+58 -0)

📄 Description

No description provided

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/ESFT/pull/3 **Author:** [@ZihanWang314](https://github.com/ZihanWang314) **Created:** 8/10/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (2) - [`3fdfb61`](https://github.com/deepseek-ai/ESFT/commit/3fdfb61e2745c2ea44688f3726349ed829688657) add training code - [`07c4f84`](https://github.com/deepseek-ai/ESFT/commit/07c4f846c97c2903c3261424ef950f7cee3b22c0) update eval and readme ### 📊 Changes **19 files changed** (+2864 additions, -158 deletions) <details> <summary>View changed files</summary> ➕ `.gitignore` (+1 -0) 📝 `README.md` (+42 -17) ➕ `configs/base.yaml` (+31 -0) ➕ `deepseek/__init__.py` (+0 -0) ➕ `deepseek/configuration_deepseek.py` (+206 -0) ➕ `deepseek/modeling_deepseek.py` (+1918 -0) 📝 `esft.py` (+25 -8) ➕ `eval_multigpu.py` (+92 -0) 📝 `scripts/eval.sh` (+15 -3) 📝 `scripts/eval_expert.sh` (+7 -5) ➕ `scripts/expert/generate_expert_config.py` (+97 -0) ➕ `scripts/expert/get_expert_scores.py` (+78 -0) ➖ `scripts/generate_expert_config.py` (+0 -50) ➖ `scripts/get_expert_scores.py` (+0 -75) ➕ `scripts/train.sh` (+12 -0) ➕ `scripts/train_ep.sh` (+11 -0) ➕ `train.py` (+117 -0) ➕ `train_ep.py` (+154 -0) 📝 `utils.py` (+58 -0) </details> ### 📄 Description _No description provided_ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
bsakaguchi 2026-10-26 21:06:50 +00:00
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/ESFT#20
No description provided.