Error when running in 4bit with bitsandbytes
#207 opened 8 days ago
by
Lue-C
Addressing Incomplete Answers Generated from Large Contexts
#206 opened 13 days ago
by
pooja03
Model gating?
1
#204 opened 16 days ago
by
gawotik
Upload 2 files
2
#203 opened 16 days ago
by
chakkakrishna
RAG, prompt and memory with Mixtral
8
#201 opened 20 days ago
by
edoyen
Any Update on mistralai/Mixtral-8x7B-Instruct-v0.2 ?
#200 opened 21 days ago
by
bayraktaroglu
Input validation error: `inputs` tokens + `max_new_tokens` must be <= 2048. on Mixtral8x7b 32K token
2
#199 opened 21 days ago
by
sunnykusawa
Warning message for right side padding even after setting padding_side="left"
#198 opened 22 days ago
by
mbismay
Input token size issue, does it realy supports 32k tokens?
1
#197 opened 22 days ago
by
sunnykusawa
infinite carriage returns
#195 opened 23 days ago
by
lowfreak
What is the stop token for this model please
2
#194 opened 23 days ago
by
NigelTheMaker
[AUTOMATED] Model Memory Requirements
#193 opened 27 days ago
by
model-sizer-bot
Problem while running on multiple GPUs
#192 opened 28 days ago
by
venkilfc
Discrepancy between kv_proj in .safetensors and .pt?
1
#191 opened about 1 month ago
by
kolinko
Missing Output problem
4
#190 opened about 1 month ago
by
chaydaroglu
Instruct-finetuning dataset
#189 opened about 1 month ago
by
Andriy
when I run it in multi-gpus by accelerate, it has an AttributeError
#188 opened about 1 month ago
by
waleyWang
What is the actual context size of mistralai/Mixtral-8x7B-Instruct-v0.1 model
3
#186 opened about 1 month ago
by
Pradeep1995
How to All Utilize all GPU's when device="balanced_low_0" in GPU setting
2
#185 opened about 1 month ago
by
kmukeshreddy
Update README.md
#184 opened about 1 month ago
by
alamati
Is function calling (tools) supported?
1
#183 opened about 1 month ago
by
TomerRobusta
Getting cut-off responses with Mixtral 8x7B-Instruct-v0.1 mostly in Date of Birth years
1
#182 opened about 1 month ago
by
keskival
How can I run it on multiple GPUs?
11
#181 opened about 1 month ago
by
barbery
Where is the mixtral-8x7b's tokenizer encoder? Is there a specific repository or node module?
1
#180 opened about 1 month ago
by
RamanSB
What is the max token limit on this model?
2
#179 opened about 1 month ago
by
RamanSB
Finetuning Mixtral 8x7B Instruct-v0.1 using Transformers
2
#178 opened about 1 month ago
by
Ateeqq
Update chat template to resemble the prompt as stated in the model card.
2
#176 opened about 2 months ago
by
nilsec
max_sequence_length
1
#175 opened about 2 months ago
by
Ravnoor1
Awesome. I Got Very Good Responses, However...
#174 opened about 2 months ago
by
Phil337
How to run the full model ?
2
#171 opened about 2 months ago
by
dounykim
Is there a working/quantized/exl2 (etc) version that will fit on a single 24GB video card (4090)
2
#170 opened 2 months ago
by
cleverest
403 error
1
#169 opened 2 months ago
by
minhphan-qbe
Adding Evaluation Results
#168 opened 2 months ago
by
leaderboard-pr-bot
Rename README.md to RegulusOne
#167 opened 2 months ago
by
Theguy666
Help: CUDA Out of Memory. Hardware requirements.
2
#147 opened 2 months ago
by
zebfreeman
Update README.md
#146 opened 2 months ago
by
frank76rm
Experimental use
#144 opened 2 months ago
by
yassineelkhadiri14
TemplateError: Conversation roles must alternate user/assistant/user/assistant/...
4
#143 opened 2 months ago
by
quamer23
Is instruction format necessary
2
#142 opened 2 months ago
by
supercharge19
[AUTOMATED] Model Memory Requirements
3
#141 opened 2 months ago
by
model-sizer-bot
Update README.md
#140 opened 3 months ago
by
woodyk
Cuda Out of memory issue when deploying mistralai/Mixtral-8x7B-Instruct-v0.1 on AWS "ml.g5.48xlarge"
1
#139 opened 3 months ago
by
sonalisbapte
slow response
1
#138 opened 3 months ago
by
bhavanam2809
Sparsity in mixtral
#137 opened 3 months ago
by
dpk17
Request: DOI
#136 opened 3 months ago
by
Sonny03
Running in Multi-gpu's
5
#134 opened 3 months ago
by
kmukeshreddy
Update README.md
#133 opened 3 months ago
by
gmverbas
How to format custom dataset to finetune Mixtral with TRL SFT script?
#132 opened 3 months ago
by
icpro