[PR #699] Fintune swap tokenizer #291

Open
opened 2026-10-26 21:05:28 +00:00 by bsakaguchi · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepSeek-Coder/pull/699
Author: @taras-sereda
Created: 5/18/2026
Status: 🔄 Open

Base: main ← Head: taras/fintune-swap-tokenizer


📝 Commits (2)

  • da94445 update requirements for both inference and finetuning
  • 9394394 finetune deepseek coder with tokenizer from other model

📊 Changes

3 files changed (+135 additions, -15 deletions)

View changed files

📝 finetune/finetune_deepseekcoder.py (+124 -8)
📝 finetune/requirements.txt (+2 -2)
📝 requirements.txt (+9 -5)

📄 Description

This PR allows finetuning DeepSeek coder with a tokenizer take from another model.
Useful for tuning a speculator with the target model's tokenizer.


🔄 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/DeepSeek-Coder/pull/699 **Author:** [@taras-sereda](https://github.com/taras-sereda) **Created:** 5/18/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `taras/fintune-swap-tokenizer` --- ### 📝 Commits (2) - [`da94445`](https://github.com/deepseek-ai/DeepSeek-Coder/commit/da94445581c0f72df3becd1e8bc0fad666a96fb4) update requirements for both inference and finetuning - [`9394394`](https://github.com/deepseek-ai/DeepSeek-Coder/commit/939439469153d9c00353ea67af2e40984309abf6) finetune deepseek coder with tokenizer from other model ### 📊 Changes **3 files changed** (+135 additions, -15 deletions) <details> <summary>View changed files</summary> 📝 `finetune/finetune_deepseekcoder.py` (+124 -8) 📝 `finetune/requirements.txt` (+2 -2) 📝 `requirements.txt` (+9 -5) </details> ### 📄 Description This PR allows finetuning DeepSeek coder with a tokenizer take from another model. Useful for tuning a speculator with the target model's tokenizer. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Sign in to join this conversation.
No milestone
No project
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/DeepSeek-Coder#291
No description provided.