Align tokenizer with mistral-common
1
#45 opened 2 days ago
by
Rocketknight1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1660312628256-60ba519750effef3a58beac3.png)
Hardware requirements to use mistralai/Codestral-22B-v0.1
1
#44 opened 4 days ago
by
tzak86
Add chat_template to tokenizer_config.json
#39 opened 15 days ago
by
Albhebvvsbbe
Run Codestral on Google Colab or Kaggle
#38 opened 19 days ago
by
mohammad1998
Update config.json
1
#36 opened 20 days ago
by
rameshjhar480
Optimizing with the transformers library
#35 opened 21 days ago
by
Taylor658
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641b754d1911d3be6745cce9/GXN8mEmaq3rfITRrw7GeZ.jpeg)
Why "Mistral Inference" and why your own tokenizer formats?
#34 opened 21 days ago
by
winddude
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62fd57e9c1588e1d4c699edc/Y3tvhM3gCj_I6WuZUBFIN.jpeg)
NS1
#33 opened 24 days ago
by
nishan3000
test2
2
#32 opened 24 days ago
by
yangwei999
Knowledge cutoff date
2
#30 opened 25 days ago
by
aravindsr
Sample code using HF
1
#29 opened 25 days ago
by
vanshils
Update README.md
#28 opened 26 days ago
by
Criztov
How to convert the weight to HF compatible?
7
#26 opened 27 days ago
by
salaki
Question about consolidated.safetensors vs model*.safetensors
#25 opened 28 days ago
by
JineLD
New tokenizer.json doesn't match tokenizer.model.v3, there's no [SUFFIX], [MIDDLE] and [PREFIX] tokens.
1
#24 opened 28 days ago
by
mukel
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64d784d0fd0b55d50184f485/4mdr0g8BzE1jOWYAGdtRC.jpeg)
can inference with vllm?
#21 opened 28 days ago
by
amosxy
Why does this have 518 likes without any download, inference api or spaces?
3
#20 opened 29 days ago
by
GPT007
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/AXnwP_G2WkJ0gkBepd_t7.png)
How to load in multi-gpu instance ?
4
#19 opened 29 days ago
by
aastha6
Is it a pretrained/base model or instruct model?
1
#17 opened 29 days ago
by
Sinsauzero
how to fine tune this model?
4
#16 opened 29 days ago
by
leo009
![](https://cdn-avatars.huggingface.co/v1/production/uploads/646334477e9025b09bd57d75/MDysdEWFWeJQDeDOLmdvI.png)
What is the context size on this model? And it does not appear to deal with JSON, function calling well.
1
#15 opened 29 days ago
by
BigDeeper
Can I use the model's output code to develop software for a commercial website? (I am a MERN stack developer working in a company)
1
#14 opened 30 days ago
by
nib12345
Disclosing training data
#13 opened 30 days ago
by
Vipitis
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1644786625098-noauth.jpeg)
Fill in the Middle evaluation benchmark
1
#12 opened about 1 month ago
by
phqtuyen
No [PREFIX] and [SUFFIX] in tokenizer vocab
5
#10 opened about 1 month ago
by
Vokturz
Update README.md
#9 opened about 1 month ago
by
machinez
License
3
#8 opened about 1 month ago
by
mrfakename
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62e54f0eae9d3f10acb95cb9/VAyk05hqB3OZWXEZW-B0q.png)
Enabling inference
1
#7 opened about 1 month ago
by
rahgadda
How to convert to HF format?
5
#6 opened about 1 month ago
by
ddh0
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64bc5b4512d00c4589dfa8a6/E-jSfIcXcPTQanocQs78P.png)
What does the tokenization for fill-in-the-middle requests look like?
2
#5 opened about 1 month ago
by
XeIaso
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63041e2ceedc089484c8415f/N4wDfkXMfAQLyOBO9bkiA.png)
bpmn modeling
#4 opened about 1 month ago
by
alibama
We are so back
5
#3 opened about 1 month ago
by
nanowell