forum

1495 threads · Page 19 of 30

Error loading the saved model 10 messages
Open
Finetune InternVL2_5-4B 3 messages
What's the best unrestrained model? 3 messages
Solved
Nightly version: Unexpected indentation error 8 messages
Open
LLama 3.1 8B fine-tuning output repeats input 3 messages
Open
Llama 3B Fine Tuning Notebook Broken Outside Colab 3 messages
Open
Hi everyone,I am trying to fine-tune the Llama 3.1 8B 4bit model using Unsloth for a specific task 2 messages
What's the cheapest/best way to host a model? 2 messages
Puzzle Clarification 16 messages
Open
Fine-tuning LLM model for Sentiment Analysis 33 messages
Save model to VLLM 5 messages
Solved
Invalid device ordinal 2 messages
Open
Fine tuning, RAG or combination of both? 3 messages
Trying to# Save to q4_k_m GGUFmodel.push_to_hub_gguf(FINETUNED_MODEL_NAME, tokenizer, quantization 3 messages
Converting the 16-bit vision export to 4-bit gguf? 7 messages
Unsuccessful fine-tuning llama 3 and llama 3.1 35 messages
How to host the model in google colab 20 messages
Overall Knowledge Questions 78 messages
Open
Saving only lora adapters as GGUF 5 messages
push_to_hub_gguf broken? 4 messages
Install torch, xformers, trl, unsloth in Linux machine venv 5 messages
Saving files to gguf 4 messages
Running llms on mixture of cpu and gpus to get more memory 88 messages
Runtime Error 6 messages
Fine Tuning LLM without success 2 messages
SFTTrainer 6 messages
Multi-class classification using Unsloth 2 messages
Open
How to Create Own bnb-4bit Models 2 messages
Help with Training Data for Llama 3.1 2 messages
OOM Recoverability? 2 messages
Open
Unsloth v Instructlab 2 messages
Can't proceed past downloading model 2 messages
Open
Help with gpu isses 10 messages
Open
Custom Base Model Suppport for GRPO 7 messages
SFT IS BROKEN (USING YOUR TUTOR COLAB) 30 messages
error loading model: error loading model vocabulary: cannot find tokenizer merges in model file 25 messages
The issue is the embed_tokens & lm_head not trainable, which will cause NaNs. 5 messages
After i fine tuned a model on unsloth, can i use it on Ollama and Open WebUI? 2 messages
GRPO not working at all after training? 63 messages
Vision finetune (qwen2-VL) notebook OOM 26 messages
Getting tps below expectations (IQ1_S 131GB) 3 messages
Open
can I directly run these safetensors on ollama? 8 messages
Porting the colab notebook to paperspace 12 messages
Open
Getting error "does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model" 5 messages
Open
Curious OOM when using "unsloth" gradient checkpointing 6 messages
Open
GRPO Notebook not working on a local 3090 with 4-bit loading enabled. 2 messages
Solved
CUDA OOM When trying to load Qwen2.5-7B instruct in GRPO notebook 16 messages
Solved
How to maximize speed with 200GB VRAM, 251GB RAM DDR5 and 56 cores (112 threads) for Q2_K_XL R1? 5 messages
My model doesn't upload to HF from the notebook 9 messages
Open
Need a road map on how to implement a search/suggestion based AI 10 messages