Need Help fine tuning llama3 with torchtune
|
|
0
|
29
|
July 16, 2024
|
Performance of the idefics-9b
|
|
0
|
3
|
July 16, 2024
|
How to convert LlavaLlamaForCausalLM based models to GGUF
|
|
0
|
30
|
July 16, 2024
|
Best practices to use models requiring flash_attn on Apple silicon macs (or non CUDA)?
|
|
1
|
65
|
July 16, 2024
|
Cost Prediction of nvidia nim nv-embed-v1
|
|
0
|
35
|
July 15, 2024
|
Ignore_value in maskformer and oneformer configs
|
|
0
|
6
|
July 15, 2024
|
ControlNet "resume from checkpoint"
|
|
0
|
18
|
July 15, 2024
|
VRAM keeps increasing during sequential llama2-13b inferencing
|
|
1
|
242
|
July 15, 2024
|
Unsupervised fine tuning mistral 7b
|
|
5
|
1457
|
July 14, 2024
|
A very basic Hugging Face LLM API access
|
|
0
|
40
|
July 14, 2024
|
Provided filename does not match any environments
|
|
6
|
1121
|
July 14, 2024
|
Model Recommendation for table extraction from PDF
|
|
3
|
2099
|
July 14, 2024
|
Streamlit + Llama 3, takes too much gpu memory?
|
|
0
|
50
|
July 13, 2024
|
Why can't able to load the Meta/Llama-2 model from local path which we download from Huggingface use Git and save on my local?
|
|
0
|
45
|
July 12, 2024
|
Access of LLaMA-2-7b-chat-hf Model
|
|
0
|
73
|
July 11, 2024
|
Model for High FPS (20) for object detection in RaspberryPi5
|
|
0
|
67
|
July 11, 2024
|
BartForConditionalGeneration: Adding additional layers of embedding
|
|
2
|
148
|
July 11, 2024
|
How do i finetune a phi-2 model which has been pre trained on a specific dataset
|
|
0
|
125
|
July 10, 2024
|
Inference widget not loading model
|
|
0
|
49
|
July 10, 2024
|
Mmed_Llama_3_8b_retraining
|
|
0
|
63
|
July 10, 2024
|
Llama-2 CUDA OOM during inference but not training
|
|
2
|
101
|
July 10, 2024
|
How to load only a part of pretrained weights?
|
|
0
|
53
|
July 9, 2024
|
Duplicate inputs in contrastive loss e.g. CLIP
|
|
0
|
54
|
July 8, 2024
|
How to separately use T5 decoder
|
|
4
|
2420
|
July 7, 2024
|
Saving a model and loading it
|
|
3
|
37348
|
July 5, 2024
|
Domain-specific code translation with llama
|
|
0
|
62
|
July 5, 2024
|
Convert model clip to onnx
|
|
0
|
69
|
July 5, 2024
|
Data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 6952 column 3
|
|
1
|
688
|
July 4, 2024
|
Correct way to pass context to llama.cpp server
|
|
0
|
130
|
July 4, 2024
|
T5-small performance degradation with larger dataset: seeking advice
|
|
0
|
52
|
July 4, 2024
|