forum

1495 threads · Page 3 of 30

unsloth in DGX Spark 6 messages
Unsloth Studio Website no styling 8 messages
Solved
I am unable to access anything other than the chat 15 messages
[FAILED] llama.cpp build failed at step: cmake configure 55 messages
long context 2 messages
Open
DAC dataset needs 'audio' and 'text' columns, got: ['instruction', 'input', 'output'] 77 messages
Unsloth studio point to existing models folder? 7 messages
Open
Unsloth Documentation Changes 2 messages
Qwen3.5-4B SFTTrainer ignores "text" column & VL processor breaking text-only finetuning 5 messages
Open
Intel mixed setup 491 messages
Website not working 24 messages
Open
Ask an experience in fine tuning using synthetic data 7 messages
Docs Contribution Request 2 messages
Open
[Regression?] Official 500K gpt-oss-20b notebook now fails with CUDA OOM 3 messages
Fine-tuning Qwen3.5 to play chess and predict the next move 15 messages
How can I install qwen 3.5 4b Q8 in my M4 mac? 2 messages
Newbie question, Xeon + 64GB ECC RAM and old AMD RX480 8GB VRAM 18 messages
unable to convert to fine tunned model to gguf 22 messages
Fix misspelling in Qwen3.5 Documentation 4 messages
Solved
[Unsloth Ecosystem] DeepSeek-OCR-2 deployment 98% complete on RTX 2080 Ti (Turing) – stuck on final 9 messages
Open
OpenEnv hackathon X unsloth 12 messages
Training hangs at step 1 when fine-tuning Qwen 3.5 33 messages
Solved
Using smart_resize from qwen_vl_utils when finetuning qwen3-vl 2 messages
Is the version uploaded 4 days ago for Qwen3.5-122B already updated with the tool-using fixes? 2 messages
Fast Inference OOMs with vLLM for GRPO 28 messages
Solved
Phi 4 mini doesn't work with Unsloth 26 messages
Tiny doco error 2 messages
Open
Unable to merge lora adapter with base model, after doing CPT on a model with tied_embeddings=True 3 messages
gpt-oss-(20B)-GRPO.ipynb 'ParameterModule' is not defined 7 messages
Solved
Finetune support for Qwen3.5-35B-A3B 2 messages
Solved
Trained Unsloth Mistral-7B with 1024 max_seq_length — now inference truncates anything >1024. How t 3 messages
Solved
ValueError when running inference with Qwen3-VL-8B LoRA checkpoint (FastVisionModel) 13 messages
Open
GLM Flash GGUF Optimizations 10 messages
Solved
Llama-3.3-70B-Instruct Clarity 3 messages
GLM 4.7 Flash - Notebook Optimization 3 messages
Open
Help: Need to improve performance from a 7b deepseek model or qwen 8b 5 messages
Open
Fine-tune MoE Models 12x Faster with Unsloth 38 messages
GLM 4.7 Flash - Notebook finetuning - Issues 13 messages
Solved
MoE 4bit quant fine tuning 5 messages
Open
Request for Unsloth quants: Nanbeige4.1-3B 6 messages
Request for Unsloth quants: MiniMax M2.5 5 messages
Numba needs NumPy 2.2 or less. Got NumPy 2.4. on official docker image 2 messages
GLM-5-GGUF disable thinking 5 messages
GPT-OSS 20B (MoE) – FT → GGUF → Ollama → Triton (vLLM) | Need Guidance I’m fine-tuning GPT-OSS 20B 3 messages
Request an enterprise account for reinforcement learning fine-tuning (GRPO) 11 messages
GLM 4.7 Flash (30B-A3B) - bnb 4 bit? 2 messages
Types of RL algorithms supported 3 messages
EmbeddingGemma (300M) fine-tuning notebook throwing error while pushing to HF 16 messages
GKDTrainer + Unsloth 4 messages
Error(s) in loading state_dict for NextDiT 4 messages