|
Custom Safety checker class
|
|
0
|
61
|
July 2, 2024
|
|
Meta-Llama-3-8B-Instruct: "max_new_tokens" is not working for /v1/chat/completions
|
|
1
|
353
|
July 2, 2024
|
|
Fine tune with SFTTrainer
|
|
17
|
5257
|
June 28, 2024
|
|
Implentation of QA-LoRA
|
|
2
|
369
|
June 25, 2024
|
|
Inference API for fine-tuned model not working: No package metadata was found for bitsandbytes
|
|
14
|
2652
|
June 24, 2024
|
|
AttributeError: 'LangchainEmbedding' object has no attribute '_langchain_embedding;
|
|
0
|
142
|
June 21, 2024
|
|
Disable regex use when training a new GPT2 Tokenizer
|
|
0
|
108
|
June 21, 2024
|
|
How to use set_transform when map becomes unfeasible?
|
|
2
|
108
|
June 19, 2024
|
|
Text classification training on long text
|
|
3
|
3101
|
June 18, 2024
|
|
Accelerate - WeightedRandomSampler Dataloader
|
|
1
|
109
|
June 18, 2024
|
|
Which EPYC CPU for inferencing? Self-hosted build
|
|
0
|
117
|
June 16, 2024
|
|
Accelerate socket timeout on multi-node LLM training
|
|
0
|
129
|
June 14, 2024
|
|
How to ensure my custom Trainer is using my custom TrainerState and TrainerControl?
|
|
1
|
111
|
June 14, 2024
|
|
FSDP with Trainer class: AlgorithmError: ValueError('Cannot flatten integer dtype tensors'), exit code: 1
|
|
0
|
229
|
June 13, 2024
|
|
Fine-tuning `mistral-7B` for classification with QLoRA using peft
|
|
2
|
231
|
June 13, 2024
|
|
Using LLM cache
|
|
0
|
93
|
June 12, 2024
|
|
Finetuning with SFTtrainer
|
|
1
|
214
|
June 12, 2024
|
|
Which weights change when fine-tunning a pre-trained model?
|
|
3
|
231
|
June 11, 2024
|
|
Creating a docvqa dataset - gt_parses
|
|
1
|
487
|
June 11, 2024
|
|
Deployment of finetuned Mistral for Classification and Generation
|
|
4
|
175
|
June 10, 2024
|
|
How to fix RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
|
|
1
|
732
|
June 10, 2024
|
|
Error Training Vision Encoder Decoder for Image Captioning
|
|
8
|
2523
|
June 8, 2024
|
|
Inference after QLoRA fine-tuning
|
|
8
|
4520
|
June 7, 2024
|
|
SAMModel output size different to the input
|
|
2
|
185
|
June 6, 2024
|
|
MaskFormer Jagged Edges Issues of output masks
|
|
1
|
206
|
June 5, 2024
|
|
4:3 to 16:9 Infill
|
|
0
|
72
|
June 4, 2024
|
|
Deploying Whisper Based Live Transcription for 1000 Concurrent users
|
|
0
|
177
|
June 1, 2024
|
|
Running multiple instances on GPU
|
|
0
|
132
|
June 1, 2024
|
|
Quantization not yet implemented
|
|
0
|
94
|
June 1, 2024
|
|
Fine-tuning Mistral/Mixtral for sequence classification on long context
|
|
2
|
2442
|
May 29, 2024
|