Giters
tloen
/
alpaca-lora
Instruct-tune LLaMA on consumer hardware
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
18080
Watchers:
157
Issues:
466
Forks:
2159
tloen/alpaca-lora Issues
decapoda-research/llama-7b-hf is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
Updated
21 days ago
Comments count
1
Finetune scenarios
Updated
21 days ago
AttributeError: module 'gradio' has no attribute 'inputs'
Updated
a month ago
Comments count
13
decapoda-research/llama-7b-hf no longer accessible
Updated
a month ago
Comments count
4
Are the saved models (either adapter_model.bin or pytorch_model.bin) only 25-26MB in size?
Updated
a month ago
Comments count
5
failed to run on colab: ModulesToSaveWrapper has no attribute `embed_tokens`
Updated
a month ago
Is there a way to check if this training is all done?
Updated
a month ago
Is it possible to combine alpaca-lora with RAG
Updated
a month ago
did not receive grad for rank 2,base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight
Updated
a month ago
Comments count
2
Loading a quantized checkpoint into non-quantized Linear8bitLt is not supported
Updated
2 months ago
Fine-tune argument resume_from_checkpoint starts from scratch instead of from checkpoint
Updated
2 months ago
Comments count
1
safetensors_rust.SafetensorError: Error while deserializing header: InvalidHeaderDeserialization
Updated
2 months ago
Comments count
14
LAION Open Assistant data is already released
Updated
2 months ago
The weights are not updated
Updated
4 months ago
Load_in_8bit causing issues: Out of memory error with 44Gb VRAM in my GPU or device_map error
Updated
4 months ago
Comments count
1
generate error after hit submit btn
Updated
4 months ago
Errors of tuning on 70B LLAMA 2, does alpaca-lora support 70B llama 2 tuning work?
Updated
4 months ago
is there any flag to mark the model is safetensors or pickle format?
Updated
4 months ago
Please update the template for Llama-2 chat completion
Updated
4 months ago
Comments count
1
can't load tokenizer
Updated
4 months ago
Comments count
2
When I set load_in_8bit=true, some errors occurred....
Updated
4 months ago
Error when loading lora weights
Closed
5 months ago
Comments count
2
generate error
Closed
5 months ago
Comments count
1
CUDA out of memory : I am using Colab T4 GPU
Updated
5 months ago
Comments count
2
All adapter_model.bin is the same
Updated
5 months ago
Comments count
2
Cannot backpropagate on the loss
Updated
5 months ago
load_dataset error with Kaggle environment
Updated
5 months ago
No output when running generate.py
Closed
5 months ago
May I ask if this project supports internlm
Updated
5 months ago
GPU UTIL fluctuates wildly
Updated
5 months ago
Comments count
1
RuntimeError: shape '[32, 2, 64, 4096]' is invalid for input of size 26214400
Closed
6 months ago
Comments count
1
Possible bugs when using generate_response for batched inference
Updated
6 months ago
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1033, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '<'.
Updated
6 months ago
Comments count
1
i want to know how to not to use the wandb tool at the finetune.py
Closed
6 months ago
How to control the save path of downloaded files
Closed
7 months ago
[Question] about fine-tune Qualitative question and Quantitative question
Updated
7 months ago
Comments count
2
Unable to determine this model’s pipeline type. Check the docs -- Huggingface Inference
Updated
7 months ago
lora for text classification
Updated
7 months ago
[Question] about pipeline for fine-tuning with conversational question answering dataset.
Updated
7 months ago
[Question] about combining prompt with input and no input for generating prompt fine-tune
Closed
7 months ago
Is the generation_config important during LoRa fine-tuning?
Updated
7 months ago
llama and llama2 finetune
Updated
7 months ago
Use new trained of LoRA model that completely unable to generate content related to the customized data
Updated
7 months ago
Unable to utilize multi card computing
Updated
7 months ago
Sparticle/llama-2-7b-chat-japanese-lora fails to load due to "State dict should either all have the prefix 'base_model.model.' or not"
Updated
7 months ago
OSError: exception: access violation reading 0xFFFFFFFFA4713EA0
Updated
7 months ago
does it can used in llama2.c?
Updated
8 months ago
Comments count
1
got same answer as pre-trained base model
Updated
8 months ago
Comments count
1
CUDA error: an illegal memory access was encountered
Updated
8 months ago
Release Open source Chinese NSFW LLM.
Updated
8 months ago
Previous
Next