Align tokenizer with mistral-common
#158 opened 4 days ago
by
Rocketknight1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660312628256-60ba519750effef3a58beac3.png)
Getting weird (same) response everytime through Mistral7B
5
#157 opened 9 days ago
by
pawankumar-108
Request: DOI
1
#156 opened 11 days ago
by
SriK007
hamzaalgohary
#155 opened 19 days ago
by
hamzaalgohary
Mistral sliding_window implementation and flash_attn_func
#154 opened about 1 month ago
by
SadRick
size of hidden layers and sliding window attention - dimension is the same, 4096. Is that for a reason?
2
#153 opened about 1 month ago
by
keval-sha
Need help, Getting HfHubHTTPError 429 Client Error: Too Many Requests for url
1
#152 opened about 1 month ago
by
ashishomi89
Request: DOI
#151 opened about 1 month ago
by
irkan
Update README.md
#150 opened about 2 months ago
by
WzY1924561588
Service Unavailable
#149 opened about 2 months ago
by
glitterllama
Unable to access Mistral-7B-v0.1 from AWS sagemaker
#148 opened 2 months ago
by
Tecena
Cannot access get repo
7
#147 opened 2 months ago
by
Dav22
KeyError: 'base_model.model.model.layers.0.mlp.down_proj.lora_A.weight'
#146 opened 2 months ago
by
DevSelego
Inference: CUDA out of memory error
#145 opened 2 months ago
by
Tecena
Issue with HuggingFace pipeline with RouterOutputParser OutputParserException: Got invalid return object. Expected key destination to be present, but got {}
#144 opened 2 months ago
by
Jyotiyadav
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1657270899620-62b8ab382578051c79b1ed8b.jpeg)
ModelError: An error occurred (ModelError) when calling the InvokeEndpoint
#143 opened 3 months ago
by
Tecena
End of sentence (</s>) does not appear to be predicted in reasoning prompts
2
#142 opened 3 months ago
by
psneto
KeyError:'mistral"' while finetuning mistral-7B-v0.1 in aws sagemaker
2
#141 opened 3 months ago
by
Tecena
Finetuning produces noisy output
#139 opened 3 months ago
by
sriramk750
When will be v0.2 updated in Huggingface?
#138 opened 3 months ago
by
SlytherinGe
Unsupervised training of Mistral for Domain-Specific Inference
#135 opened 3 months ago
by
H2dddhxh
Lora fine tuning for text classification with Peft
#134 opened 3 months ago
by
farbodKMSE
Easiest way to fine tune Mistral-7B
1
#133 opened 3 months ago
by
exnrt
Keep Responding in the wrong language despite the prompt template instructing to reply in a specific language
6
#132 opened 4 months ago
by
tdecae
![](https://cdn-avatars.huggingface.co/v1/production/uploads/652002b2fabe0021d2ebec5d/WlYBQzxnAt4o9MSVOZfnF.jpeg)
Finetune Mistral 7B full parameters without LORA
2
#131 opened 4 months ago
by
HuggingPanda
Very long response time
4
#130 opened 4 months ago
by
farbodKMSE
Fine Tuning for Classification
4
#129 opened 4 months ago
by
MUHAMMAD-SOHAIL-ZZU
Unable to inference beyond sliding window length
#128 opened 4 months ago
by
kreas
How to finetune this model mistralai/Mistral-7B-v0.1 and also merge the weights
5
#126 opened 5 months ago
by
yeniceriSGK
Pretrain?
3
#125 opened 5 months ago
by
limha
Mistral 7B produces different results when we hit via postman api
7
#124 opened 5 months ago
by
DivyaKanniah
Load and extract the model for language modeling
1
#123 opened 5 months ago
by
theodp
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65b779ed7b2f6622ccc25651/SAuxPpKqTRVhm8J2msAnJ.jpeg)
Unexpected keyword 'rope_scaling' while loading model
3
#122 opened 5 months ago
by
gandhipratik65j
Kernel crashed while loading checkpoint shards
3
#121 opened 5 months ago
by
clemennntt
Is there any way to increase the vocabulary of the tokenizer and use it fine tune the model on the new language
4
#120 opened 6 months ago
by
Tejaswi006
I hope he can respond according to the language used by the user
#118 opened 6 months ago
by
poarpeak
Fix context length in config
#117 opened 6 months ago
by
imone
![](https://cdn-avatars.huggingface.co/v1/production/uploads/61b6cbbdbfb266841ec0f24a/PHUVNOOMEw_R2CF3u-sMS.png)
Finetuning with PEFT - Some weights of MistralForSequenceClassification were not initialized from the model
6
#116 opened 6 months ago
by
RobbieTheRobot
Data collator removing eos token
#115 opened 6 months ago
by
MaBrThesis2023
Thanks to Mistral for making our dream a reality
1
#114 opened 6 months ago
by
Muhammadreza
Is SWA used during pertaining?
#113 opened 6 months ago
by
EarthWorm001
FT Mistral Generate Slowly
#112 opened 6 months ago
by
yixliu1
PEFT based Fine Tuned model hallucinates values from the fine tuning training data while inferencing.
7
#111 opened 6 months ago
by
Pradeep1995
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1599822346546-noauth.jpeg)
should we follow the same mistral prompt structure while finetuning time?
#110 opened 6 months ago
by
Pradeep1995
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1599822346546-noauth.jpeg)
npz file for apple MLX
2
#109 opened 6 months ago
by
joy2000
Error in config.json
3
#108 opened 6 months ago
by
sohamghoshml
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/UW-GHyzjoFg9GfUhMkQ8w.png)
Incomplete Output even with max_new_tokens
12
#107 opened 6 months ago
by
Pradeep1995
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1599822346546-noauth.jpeg)
can't generate embedding vector
#106 opened 7 months ago
by
philgrey
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/ixKl5PVwauxFVuRMwv-ON.jpeg)
Maximum number of input tokens ?
1
#104 opened 7 months ago
by
Kirolos
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63110da007a7682790258e54/dFOFEioi2Wp8zLYHm4ilN.jpeg)