forum
import error RuntimeError: Failed to import trl.trainer.alignprop_trainer because of the following e
128GB RAM and how much VRAM do I need to comfortable run 2.51-bit version of R1?
Llama 3.2 Vision Finetuning Unsloth - Radiography notebook not working
Database batch size error (new GRPO notebook)
Open
Can not import FastLanguageModel from unsloth in Kaggle notebook
Solved
CMake Error on Mistral_Small_22B Notebook
Lora Qwen2.5 with GRPO error
nvidia only required for unsloth?
Solved
How to fine tune on low amounts of data?
Open
How to convert the following to GUFF format?
Wondering how much GPU memory it takes to finetune, inference the 32B, 70B and 671B deepseek models
when merging 2.51-bit model files, received this error, how to fix it?
Helping out
Censorship
Json data ai integration
unsloth_windows.ps1
High training loss
Tried using Deepseek R1 (1.58bit) ... model is not loading correctly/takes forever to load
want to train a local llm using custom dataset
Open
Looking for guide on how to create bnb-4bit
Solved
trainer.train() issues with unsloth: /usr/bin/ld: cannot find -lcuda: No such file or directorycoll
TypeError: must be called with a dataclass type or instance when importing unsloth.FastLanguageModel
Open
Running out of VRAM when fine tuning for VLM
Issue with saving model step
Perplexity of dynamic quant R1 models
deepseek r1 llama cpp flash_attn requires n_embd_head_k == n_embd_head_v - forcing off
save_pretrained_gguf llama.cpp error: "quantize does not exist."
Solved
Running Deepseek-r1:8b with langchain_ollama
Poor results after fine-tuning
Quantize R-1 3B
Running the deepseek R1 via VLLM
Trying to run Deepseek-R1 Dynamic on Ollama
Solved
SFT Fine-tuning on custom data
How to save model
Training on a domain
Unsloth webui
Janus-Pro
AttributeError: 'NoneType' object has no attribute 'attn_bias'
Open
Solved
unsloth training LD error
Continuous finetuning
Finetuning on a sustainable dataset using Llama 3.2 3B
NotImplementedError: Unsloth: unsloth/phi-4
Looking for Data Scientist
Using a local dataset with WSL
Solved
image reshape to finetune llama vision?
Cant start unsloth training
Open
Lora QKV
CUDA Out of memory.... When more VRAM is available?
H100 training 4x slower than A100
All tokens getting masked, Finetuning Llama-3.2-1B-Instruct
Open