Sampler #2905
Merged
Sampler #2905
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* main: Support LoRA-GA (modelscope#2650) fix swift/Infinity-Instruct (modelscope#2651) update truncation_strategy (modelscope#2647) fix bugs (modelscope#2645) Fix post encode (modelscope#2643) fix app-ui (modelscope#2641) fix bugs & support openbuddy llama3.3 & update docs (modelscope#2638) fix dataset (modelscope#2636) fix add_default_tag (modelscope#2631) support reward model (modelscope#2628)
* commit '07f10d2a94e7342413fa7762b6ce6b101b93d130': (86 commits) Move optimizer to create_optimizer (modelscope#2851) support reward_model (modelscope#2849) 1. fix hub ignore-pattern (modelscope#2848) Fix bugs (modelscope#2838) Update base_to_chat shell (modelscope#2833) Update padding side (modelscope#2832) Fix glm4v suffix (modelscope#2829) add 'right' option for 'truncation_strategy' (modelscope#2754) update docs (specific model arguments) (modelscope#2822) fix enable_cache (modelscope#2813) fix citest (modelscope#2812) support ZhipuAI/cogagent-9b-20241220 (modelscope#2810) fix swift deploy log error (repeat log) (modelscope#2808) fix glm4v (modelscope#2806) update base_model deploy example (modelscope#2803) fix world_size (modelscope#2801) fix (modelscope#2800) support swift app (modelscope#2792) fix some web-ui bugs (modelscope#2794) fix stream infer (modelscope#2793) ... # Conflicts: # examples/train/multi-gpu/ddp/train.sh # swift/llm/__init__.py # swift/llm/argument/rlhf_args.py # swift/llm/template/base.py # swift/llm/template/template_inputs.py # swift/llm/template/utils.py # swift/llm/train/tuner.py # swift/trainers/mixin.py
* commit 'a0d0351400d522392fb4535567bab83d8b9d45b2': Support infer n parameter (modelscope#2893) support multi round dpo (modelscope#2884) fix docs (modelscope#2882) update qlora shell (modelscope#2880) fix bugs (modelscope#2876) fix citest (modelscope#2873) Support ppo (modelscope#2783) fix bugs (modelscope#2869) Update agent demo (modelscope#2867) support mps (modelscope#2866) fix vllm video (modelscope#2864) support reward model train (modelscope#2862) fix jsonl writer (modelscope#2860) Support quant bert reward (modelscope#2859) # Conflicts: # examples/train/rlhf/ppo.sh # swift/trainers/__init__.py # swift/trainers/mixin.py # swift/trainers/rlhf_trainer/ppo_trainer.py
* commit '65e4b26cc433878dbb4d67b0d1ae97287814bfa4': fix link & bug (modelscope#2902) Add phi4 (modelscope#2895) fix infer engine (modelscope#2898) Fix qwen vl eval (modelscope#2892)
Jintao-Huang
approved these changes
Jan 13, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR type
PR information
Write the detail information belongs to this PR.
Experiment results
Paste your experiment result here(if needed).