Running a 4-bit Quantized 7B Model on a PC: Feasibility and Insights
4
#109 opened about 1 year ago
by
edw-hug-face
How to get result as good as Hugging Face Chat Mixtral-8x7b-Instruct
9
#107 opened about 1 year ago
by
Panckackes
FR Discutions ouverte
3
#105 opened about 1 year ago
by
Pablito2fois
Rapport d'étonnement
#104 opened about 1 year ago
by
YannCHANET
How to use transfimer
#100 opened about 1 year ago
by
sethdwumah
SFT is so BAD
#99 opened about 1 year ago
by
GokhanAI
8bit quantization error
1
#98 opened about 1 year ago
by
lovelyfrog
Key Error : Mixtral
8
#96 opened about 1 year ago
by
jdjayakaran
Train the Model on Confluence
1
#95 opened about 1 year ago
by
icemaro
Run Mistral model on Remote server
6
#94 opened about 1 year ago
by
icemaro
Cuda Error
1
#93 opened about 1 year ago
by
HuggySSO
Not supported with TGI
3
#92 opened about 1 year ago
by
abhishek3jangid
deepspeed load mixtral-8x7B hang or oom
1
#91 opened about 1 year ago
by
guowl
Add MOE (mixture of experts) tag
#90 opened about 1 year ago
by
davanstrien

Update README.md
#89 opened about 1 year ago
by
schuyler12
Failure in loading the model on AWS
8
#88 opened about 1 year ago
by
bweinstein123
Hardware Requirements
6
#86 opened about 1 year ago
by
ShivanshMathur007
Response content was truncated
19
#84 opened about 1 year ago
by
ludomare
Best parameter setting for Mixtral model on the text-generation task
#83 opened about 1 year ago
by
kmukeshreddy

Any hints on prompt to reduce / stop hallucinations
1
#82 opened about 1 year ago
by
dnovak232
Still the best Mixtral based instruct model. We should change that
#81 opened about 1 year ago
by
rombodawg

Could not convert to integer: 3221225477 error
#80 opened about 1 year ago
by
KharabinDev42
Serving the model as API on vLLM and 2 x A6000
2
#78 opened about 1 year ago
by
dnovak232
How much memory do I need for this model (on Windows)?
3
#77 opened about 1 year ago
by
roboboot
Inconsistent prompt format. Which is correct the Model card or the tokenizer_config.json?
6
#75 opened about 1 year ago
by
lemonflourorange
can not run sft full finetuning.
9
#74 opened about 1 year ago
by
hegang126
[Chinese Version] Mixtral-8x7B model | 中文Mixtral-8x7B模型
#73 opened about 1 year ago
by
wangrongsheng

Update the deprecated Flash Attention call parameter in from_pretrained() method
#72 opened about 1 year ago
by
DeathReaper0965

can't load the model
2
#71 opened about 1 year ago
by
JayZhang1
What is the best way for the inference process in LORA in PEFT approach
8
#70 opened about 1 year ago
by
Pradeep1995

How to use system prompt?
1
#69 opened about 1 year ago
by
mznw
Is there any simple way to solve the problem of redundant output
3
#68 opened about 1 year ago
by
jjplane
Which is the actual way to store the adapters after PEFT finetuning
4
#67 opened about 1 year ago
by
Pradeep1995

Failed to import transformers.models.mixtral.modeling_mixtral because of the following error (look up to see its traceback): libcudart.so.12: cannot open shared object file: No such file or directory
1
#66 opened about 1 year ago
by
MukeshSharma
Model not loading, even with 4-bit quantization
1
#65 opened about 1 year ago
by
soumodeep-semut
did Mixtral start from Mistral or from-scratch?
1
#64 opened about 1 year ago
by
DaehanKim
How many GPUs do we need to run this out of box?
3
#63 opened about 1 year ago
by
kz919
Is this model can choose expert for every token? Or just choose two expert for a input
#62 opened about 1 year ago
by
PandaMaster
AutoTokenizer.from_pretrained show OSError
1
#61 opened over 1 year ago
by
sean29
does file with .safetensors necessary for continue sft training?
#60 opened over 1 year ago
by
hegang126
Incomplete Answers
7
#59 opened over 1 year ago
by
samparksoftwares
How can we enable continuous learning with the LLM model ?
#58 opened over 1 year ago
by
Tapendra
Inference generation extremely slow
6
#57 opened over 1 year ago
by
aledane
Optimizing Mixtral-8x7B-Instruct-v0.1 for Hugging Face Chat
1
#54 opened over 1 year ago
by
Husain
SageMaker Deployment Error
11
#53 opened over 1 year ago
by
seabasshn
killed on Loading checkpoint shards
1
#52 opened over 1 year ago
by
asmatveev
Playground?
1
#51 opened over 1 year ago
by
pbourmeau
vectorstore
3
#50 opened over 1 year ago
by
philgrey

Enable inference API
2
#49 opened over 1 year ago
by
mrfakename
