redotvideo mamba-chat issues

redotvideo / mamba-chat

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

Apache License 2.0

876 stars 68 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Question about how mamba chat training is done

#35 aravindkoti opened 1 month ago
0
Error in importing from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel in GoogleCollab

#34 ankitsrivastava637 opened 3 months ago
3
committed

#33 TeamOctaLink opened 4 months ago
0
Why choose zephyr as tokenizer?

#32 rangehow closed 4 months ago
0
sentencepiece version

#31 nuochenpku opened 4 months ago
0
I downloaded the mamba-790m file from Hugging Face to my local machine for loading and training. However, I encountered an error during the loading process, like that "Missing key(s) in state_dict: "backbone.layers.0.mixer.A_b_log""

#30 zxsdd9 closed 4 months ago
0
Is there Padding Mask when training the model?

#29 ZetangForward opened 4 months ago
0
MambaConfig' object has no attribute 'to_dict'

#28 sooko opened 4 months ago
0
update to fit MambaConfig

#27 ericoder960803 opened 4 months ago
0
How to use the model after training it ?

#26 kishore-FDI opened 4 months ago
2
Is the provided chat model trained on ultrachat_small.jsonl?

#25 shansiliu95 opened 5 months ago
1
Feature 'cvt with .bf16' requires .target sm_80 or higher Error

#24 venkat-p-r opened 5 months ago
1
Interesting chat example

#23 protima-banerjee opened 5 months ago
0
MoE https://arxiv.org/abs/2401.04081

#22 Eupham closed 5 months ago
0
ImportError: /usr/local/lib/python3.10/dist-packages/causal_conv1d_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEi

#21 venkat-p-r closed 5 months ago
1
Added check to confirm bfloat support

#20 Rohith04MVK opened 5 months ago
1
Any plan or interest to use OpenChat algorithm (https://github.com/imoneoi/openchat) to train your chat?

#19 houghtonweihu opened 5 months ago
0
Eval on benchmark?

#18 tic-top opened 6 months ago
0
Error When Inferencing

#17 SeifMosaad closed 6 months ago
1
Cant use trained model

#16 yy9996 opened 6 months ago
3
Error during training

#15 Eupham closed 5 months ago
6
Memory requirements for training

#14 pkpro opened 6 months ago
0
enhancement: better model_save

#13 getorca opened 6 months ago
0
🐞 fix: triton requirement

#12 Yingyue-L opened 6 months ago
0
Finetune on 3090 but loss equal to zero

#11 Yingyue-L opened 6 months ago
4
How could I run this on windows 10?

#10 KevinRyu opened 6 months ago
5
Colab notebook has error, numpy array used instead of torch

#9 microcoder-py closed 6 months ago
7
TypeError: MixerModel.__init__() got an unexpected keyword argument 'bos_token_id'

#8 xiechengmude opened 6 months ago
1
add missing requirements

#7 tohrnii closed 6 months ago
2
Add a simple gradio chat ui for Mamba Chat

#6 BlenderWang9487 closed 6 months ago
1
setting device for training

#5 ekg closed 7 months ago
1
Demo

#4 fakerybakery closed 6 months ago
3
Issue while installing requirements.txt

#3 wereretot opened 7 months ago
4
Bug in train_mamba.py line 53

#2 vmajor closed 7 months ago
2
Add ability to train on smaller cards like the 24GB 3090 or 4090. Fixed epoch argument.

#1 rwl4 closed 7 months ago
1