forum
FastVisionModel 4bit + save_pretrained_merged
Lower accuracy after merging adapters
How to increase VRAM allocation for unsloth ? (Or inference speed)
Qwen3-8b CPT incomplete answer issue
gemma3-n hackathon
make bnb 4bit version of mistralai/Mistral-7B-v0.3
will you guys make a finetuning notebook for falcon h1?
Open
I really dont unterstand the problem
Open
LLM.get_vllm_config doesn't exist
SFTFinetune Image Gemma3n AssertionError: expected size 16==16, stride
Persistent NaN grad norm when finetuning Gemma 3n on images
Error while trying to Finetune a already finetuned Gemma3n model
Open
Inférence endpoints
save_to_gguf_generic() got multiple values for argument 'quantization_method'
Adding a new language to a TTS model
Open
Current Dynamic 2.0 GGUF support in vLLM?
Gemma 3n Quantization Support for Image Inference
Async GRPO reward functions
Possibility of accelerating MoE training?
Open
Do you guys offer SaaS version of it?
Very slow Gemma 3 inference speeds
Open
when converting fine tuned model to GGUF i got this error :
Learning rate stays at 0 for 15 epochs when finetuning Gemma 3n
Error: 'str' object has no attribute 'str' in ModernBERT-large
Solved
converting the unsloth/gemma-3n-E4B-it-unsloth-bnb-4bit and learned lora adapters into tflite format
Open
Save fine-tuned model error
I got this error when running the fine tuning sample code for Gemma 3n :
Merge and reload gives very different output for Gemma-4b
How to run vLLM when GRPO Gemma-3n
ObjMismatchError
Open
Help with distilling/fine tuning Qwen2.5:7b
Open
Gemma 3 Inferencing Error
Solved
does the seq length we train with have to = the context length I want to use the model with?
Fine-tuned Qwen2.5-7B model loops infinitely in Ollama but works fine with transformers
Weird Token Management In llama.cpp
config error for `unsloth/medgemma-27b-it-GGUF`
CheckpointError While fine tuning Gemma 3n
TRL checkpoints with LoRA not working
Open
Training llama 3.1 8b model on odd data
RuntimeError: expected scalar type BFloat16 but found Half
Support for finetuning internvl 2.5 models
Gemma3n gguf saving broken ?
Help in training Mistral 3.2 on photos dataset
Fine-tuning on kaggle environment
Cannot start any Notebook
Understanding GPU Memory Utilization with vLLMs
Open
Help with fine-tuning llama3.1 react style agent
Open
RuntimeError: Bad in-place call: input tensor size [2097152, 1] and output tensor size [1024, 4096]
Open
Can't load g3mma 3n E2B locally on 4070 mobile
Current state of Gemma3n support