forum

1495 threads · Page 7 of 30

Fine-tune video in Qwen3 12 messages
Issue: GGUF conversion crashes Colab system 110 messages
Lora Parameter r 7 messages
Inference Endpoints Unsloth Models 6 messages
Open
Export my Qwen3 VL 8B Instruct adapter (after merging) into GGUF 45 messages
Hi, I am getting an error when trying to save my finetuned Gemma3 27B model 2 messages
issue in trainer 78 messages
[solved] Qwen3 VL Index out of bounds 10 messages
Solved
[solved] Qwen3 VL Index out of bounds 2 messages
Solved
llama.cpp slow 13 messages
Multi-GPU gpu utilization only uses one gpu at a time 13 messages
Qwen3 Vl 30b 2 messages
Infinite Waiting for Unsloth Installation 4 messages
Trouble running Advanced_Llama3_2_(3B)_GRPO_LoRA.ipynb via Apptainer on HPC 2 messages
KeyError:'align_logprobs_with_mask 2 messages
data preprocess in STT 38 messages
Unsloth: Will smartly offload gradients to save VRAM! 3 messages
i suddenly ran into this error in the STT notebook 27 messages
tips for getting better training 21 messages
Adapters format when finetuned using QLoRA 34 messages
Qwen3-VL-32B? 9 messages
gpt-oss-20b export model for vLLM 16 messages
Open Solved
plan on supporting deepseek-ocr on all the tuning? 4 messages
Qwen 2.5 VL always takes up all the vram on all gpus 6 messages
Open
How to set Video FPS for Inference and Finetuning 5 messages
how to set image max pixels 3 messages
is LLM learning? 10 messages
FailOnRecompileLimitHit on GptOssForCausalLM_forward 11 messages
I'm looking for some input from someone that is good at finetuning 8 messages
Not sure if lora gets used for inference 9 messages
gpt-oss-(20B)-GRPO Triton Compiler Error 3 messages
Solved
VLLM VRAM Usage GRPO 13 messages
Example inference code for Qwen3-VL 8B Instruct model (Vision + Language) using Unsloth 18 messages
Gemma3-1b-it fails with vllm + fullft + fast_inference 2 messages
how to use the finetuned model. 23 messages
Why ?? 5 messages
Open
NameError: name 'slice_indices' is not defined. 10 messages
Wondering how to include printing the validaltion loss during finetuning 13 messages
Inquiry About Training a Language Model on a Local Arabic Dialect 89 messages
Does unsloth have a provision to support diffusion transformers? 2 messages
SFT model giving wrong answers even after full reset (Llama-3-8B 4-bit, Unsloth SFTTrainer) 16 messages
Ling-1t - Why is Q5 smaller than Q8? 14 messages
QAT training query 13 messages
Open
NotImplementedError: Cannot copy out of meta tensor; no data! 6 messages
Open
python segmentation fault 3 messages
How can I sft GPT OSS with limited hardware 4 messages
General PEFT support 2 messages
Solved
Clarification on best dataset format for Unsloth fine-tuning 5 messages
Windows + AMD setup? 3 messages
Support InternVL3 patch 4 messages
Open