unslothai/unsloth Issues | Good First Issue

Python (64,271 star) (5,658 fork) (51 個已索引議題) (PR 指標待抓取)最近提交 2026年5月15日

正在載入倉庫議題...

議題

51 個開放索引議題

RSS Atom

開放

Docs: current Codex local llama.cpp guide does not work as written with Responses API

good first issue

unslothai/unsloth #5,141 建立於上個月 · Python · 64,271 stars

4 則留言1 個反應0 負責人

開放

[Feature] Request permission before downloading model on first run

feature requesthelp wanted

unslothai/unsloth #5,125 建立於上個月 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] Model Management in Unsloth Studio - Delete & Update Models

feature requestgood first issuehelp wanted

unslothai/unsloth #5,098 建立於上個月 · Python · 64,271 stars

1 則留言2 個反應0 負責人

開放

[Feature] Running Usloth Studion in kaggle

feature requesthelp wanted

unslothai/unsloth #4,944 建立於 2 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Feature] Unsloth studio: Set dataset streaming mode

feature requestgood first issuehelp wanted

unslothai/unsloth #4,903 建立於 2 個月前 · Python · 64,271 stars

8 則留言0 個反應1 負責人

開放

[Feature] Draft model / speculative decoding

feature requestgood first issuehelp wanted

unslothai/unsloth #4,753 建立於 2 個月前 · Python · 64,271 stars

4 則留言2 個反應0 負責人

開放

[Feature] Unsloth/ Whisper/Large-v3 - S3 Bucket connection

feature requestgood first issuehelp wanted

unslothai/unsloth #4,539 建立於 2 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Bug] Qwen3.5 vision training , error "only for image model"

help wanted

unslothai/unsloth #4,202 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] add aarch64 container images

feature requesthelp wanted

unslothai/unsloth #4,198 建立於 3 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Docs] Update DPO example to use DPOConfig instead of TrainingArguments

good first issuehelp wanted

unslothai/unsloth #4,155 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature Request] Add Idefics3 architecture support (Granite Docling VLM)

help wanted

unslothai/unsloth #4,079 建立於 3 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Feature Request] fast inference for LFM (and Mamba models)

good first issuehelp wanted

unslothai/unsloth #4,073 建立於 3 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

Request for Notebook to Fine-Tune Qwen TTS (or Alternatives Using Existing Notebooks)

feature requestgood first issuehelp wanted

unslothai/unsloth #3,961 建立於 4 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

How can I increase the GPU utilization while training / finetune an LLM with unsloth

help wanted

unslothai/unsloth #3,957 建立於 4 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人

開放

[Feature] Add FT support for the Qwen3-TTS model.

feature requestgood first issuehelp wanted

unslothai/unsloth #3,951 建立於 4 個月前 · Python · 64,271 stars

6 則留言1 個反應0 負責人

開放

How to set "reasoning_effort" of GPT-OSS during GRPO rollouts?

help wanted

unslothai/unsloth #3,949 建立於 4 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Bug] After adding import unsloth to the first line of the script, the GRPOTrainer fails to run properly; however, it works normally again once this import is removed. The Sophia optimizer interface being used was generated by an AI.

help wanted

unslothai/unsloth #3,591 建立於 6 個月前 · Python · 64,271 stars

11 則留言0 個反應0 負責人

開放

[Bug] Forced coupling between num_generations and per_device_train_batch_size in GRPOTrainer resulting in OOM

help wanted

unslothai/unsloth #3,572 建立於 7 個月前 · Python · 64,271 stars

3 則留言1 個反應0 負責人

開放

[Bug] Cannot load qwen3-vl series with lora adapter on vllm.

good first issue

unslothai/unsloth #3,560 建立於 7 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

reinforce(gspo) training didn't yield any improments

help wantedunsure bug?

unslothai/unsloth #3,485 建立於 7 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人

Python (64,271 star) (5,658 fork) (51 個已索引議題) (PR 指標待抓取)最近提交 2026年5月15日

議題

51 個開放索引議題

RSS Atom

開放

Docs: current Codex local llama.cpp guide does not work as written with Responses API

good first issue

unslothai/unsloth #5,141 建立於上個月 · Python · 64,271 stars

4 則留言1 個反應0 負責人

開放

[Feature] Request permission before downloading model on first run

feature requesthelp wanted

unslothai/unsloth #5,125 建立於上個月 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] Model Management in Unsloth Studio - Delete & Update Models

feature requestgood first issuehelp wanted

unslothai/unsloth #5,098 建立於上個月 · Python · 64,271 stars

1 則留言2 個反應0 負責人

開放

[Feature] Running Usloth Studion in kaggle

feature requesthelp wanted

unslothai/unsloth #4,944 建立於 2 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Feature] Unsloth studio: Set dataset streaming mode

feature requestgood first issuehelp wanted

unslothai/unsloth #4,903 建立於 2 個月前 · Python · 64,271 stars

8 則留言0 個反應1 負責人

開放

[Feature] Draft model / speculative decoding

feature requestgood first issuehelp wanted

unslothai/unsloth #4,753 建立於 2 個月前 · Python · 64,271 stars

4 則留言2 個反應0 負責人

開放

[Feature] Unsloth/ Whisper/Large-v3 - S3 Bucket connection

feature requestgood first issuehelp wanted

unslothai/unsloth #4,539 建立於 2 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Bug] Qwen3.5 vision training , error "only for image model"

help wanted

unslothai/unsloth #4,202 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] add aarch64 container images

feature requesthelp wanted

unslothai/unsloth #4,198 建立於 3 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Docs] Update DPO example to use DPOConfig instead of TrainingArguments

good first issuehelp wanted

unslothai/unsloth #4,155 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature Request] Add Idefics3 architecture support (Granite Docling VLM)

help wanted

unslothai/unsloth #4,079 建立於 3 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Feature Request] fast inference for LFM (and Mamba models)

good first issuehelp wanted

unslothai/unsloth #4,073 建立於 3 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

Request for Notebook to Fine-Tune Qwen TTS (or Alternatives Using Existing Notebooks)

feature requestgood first issuehelp wanted

unslothai/unsloth #3,961 建立於 4 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

How can I increase the GPU utilization while training / finetune an LLM with unsloth

help wanted

unslothai/unsloth #3,957 建立於 4 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人

開放

[Feature] Add FT support for the Qwen3-TTS model.

feature requestgood first issuehelp wanted

unslothai/unsloth #3,951 建立於 4 個月前 · Python · 64,271 stars

6 則留言1 個反應0 負責人

開放

How to set "reasoning_effort" of GPT-OSS during GRPO rollouts?

help wanted

unslothai/unsloth #3,949 建立於 4 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

help wanted

unslothai/unsloth #3,591 建立於 6 個月前 · Python · 64,271 stars

11 則留言0 個反應0 負責人

開放

[Bug] Forced coupling between num_generations and per_device_train_batch_size in GRPOTrainer resulting in OOM

help wanted

unslothai/unsloth #3,572 建立於 7 個月前 · Python · 64,271 stars

3 則留言1 個反應0 負責人

開放

[Bug] Cannot load qwen3-vl series with lora adapter on vllm.

good first issue

unslothai/unsloth #3,560 建立於 7 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

reinforce(gspo) training didn't yield any improments

help wantedunsure bug?

unslothai/unsloth #3,485 建立於 7 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人

Python (64,271 star) (5,658 fork) (51 個已索引議題) (PR 指標待抓取)最近提交 2026年5月15日

正在載入倉庫議題...

議題

51 個開放索引議題

RSS Atom

開放

Docs: current Codex local llama.cpp guide does not work as written with Responses API

good first issue

unslothai/unsloth #5,141 建立於上個月 · Python · 64,271 stars

4 則留言1 個反應0 負責人

開放

[Feature] Request permission before downloading model on first run

feature requesthelp wanted

unslothai/unsloth #5,125 建立於上個月 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] Model Management in Unsloth Studio - Delete & Update Models

feature requestgood first issuehelp wanted

unslothai/unsloth #5,098 建立於上個月 · Python · 64,271 stars

1 則留言2 個反應0 負責人

開放

[Feature] Running Usloth Studion in kaggle

feature requesthelp wanted

unslothai/unsloth #4,944 建立於 2 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Feature] Unsloth studio: Set dataset streaming mode

feature requestgood first issuehelp wanted

unslothai/unsloth #4,903 建立於 2 個月前 · Python · 64,271 stars

8 則留言0 個反應1 負責人

開放

[Feature] Draft model / speculative decoding

feature requestgood first issuehelp wanted

unslothai/unsloth #4,753 建立於 2 個月前 · Python · 64,271 stars

4 則留言2 個反應0 負責人

開放

[Feature] Unsloth/ Whisper/Large-v3 - S3 Bucket connection

feature requestgood first issuehelp wanted

unslothai/unsloth #4,539 建立於 2 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Bug] Qwen3.5 vision training , error "only for image model"

help wanted

unslothai/unsloth #4,202 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature] add aarch64 container images

feature requesthelp wanted

unslothai/unsloth #4,198 建立於 3 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

[Docs] Update DPO example to use DPOConfig instead of TrainingArguments

good first issuehelp wanted

unslothai/unsloth #4,155 建立於 3 個月前 · Python · 64,271 stars

4 則留言0 個反應0 負責人

開放

[Feature Request] Add Idefics3 architecture support (Granite Docling VLM)

help wanted

unslothai/unsloth #4,079 建立於 3 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

[Feature Request] fast inference for LFM (and Mamba models)

good first issuehelp wanted

unslothai/unsloth #4,073 建立於 3 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

Request for Notebook to Fine-Tune Qwen TTS (or Alternatives Using Existing Notebooks)

feature requestgood first issuehelp wanted

unslothai/unsloth #3,961 建立於 4 個月前 · Python · 64,271 stars

0 則留言0 個反應0 負責人

開放

How can I increase the GPU utilization while training / finetune an LLM with unsloth

help wanted

unslothai/unsloth #3,957 建立於 4 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人

開放

[Feature] Add FT support for the Qwen3-TTS model.

feature requestgood first issuehelp wanted

unslothai/unsloth #3,951 建立於 4 個月前 · Python · 64,271 stars

6 則留言1 個反應0 負責人

開放

How to set "reasoning_effort" of GPT-OSS during GRPO rollouts?

help wanted

unslothai/unsloth #3,949 建立於 4 個月前 · Python · 64,271 stars

3 則留言0 個反應0 負責人

開放

help wanted

unslothai/unsloth #3,591 建立於 6 個月前 · Python · 64,271 stars

11 則留言0 個反應0 負責人

開放

[Bug] Forced coupling between num_generations and per_device_train_batch_size in GRPOTrainer resulting in OOM

help wanted

unslothai/unsloth #3,572 建立於 7 個月前 · Python · 64,271 stars

3 則留言1 個反應0 負責人

開放

[Bug] Cannot load qwen3-vl series with lora adapter on vllm.

good first issue

unslothai/unsloth #3,560 建立於 7 個月前 · Python · 64,271 stars

5 則留言0 個反應0 負責人

開放

reinforce(gspo) training didn't yield any improments

help wantedunsure bug?

unslothai/unsloth #3,485 建立於 7 個月前 · Python · 64,271 stars

1 則留言0 個反應0 負責人