AI - Machine Learning Blog

Options
2,528
Daekeun_Kim on Jul 02 2024 06:06 AM
8,303
SeokJin_Han on May 28 2024 10:41 AM
2,618
Priya_Kedia on May 23 2024 05:56 AM
3,507
santiagxf on May 21 2024 09:10 AM
2,850
Sharmichock on May 21 2024 08:55 AM
7,558
KritiFaujdar on May 21 2024 08:30 AM
4,681
maljazaery on May 15 2024 11:38 AM
15.4K
mrajguru on May 05 2024 11:27 PM
6,857
TinaManghnani on Apr 26 2024 06:00 AM
53.1K
ThasmikaGokal on Apr 18 2024 12:39 PM
2,164
niroron on Apr 16 2024 07:09 AM
12.6K
nimoore on Apr 11 2024 06:01 PM
2,738
Sarah_Young on Mar 27 2024 09:46 PM
5,677
Sharmichock on Mar 27 2024 05:05 AM
5,385
mrajguru on Mar 26 2024 06:15 AM
6,733
Richardtso on Mar 15 2024 09:00 AM
3,098
Ruth Yakubu on Mar 08 2024 04:34 PM
3,382
shubhamsoni on Feb 28 2024 11:53 PM
39.6K
ManojBableshwar on Feb 26 2024 06:02 AM
8,508
NatalieM on Feb 21 2024 10:39 AM
2,934
antonslutsky on Feb 14 2024 10:05 AM
3,879
aishanibhalla on Jan 29 2024 03:34 PM

Latest Comments

Hi, I've created a mistral-large deployment. I want to experiment with moving my prompts from GPT-4 to Mistral. Currently, we're performing RAG using the extra_body parameter in client.chat.completions.create with GPT-4. This works fine for GPT-4, but when moving to a client = MistralClient() I can ...
0 Likes
@santiagxf Any information's/dates (Preview/GA) when Serverless API endpoints will support private networking?Thank you for your support and help.
0 Likes
Did you find a way to solve this error: The passed model cannot be used for getting predictions via predict?
0 Likes
@mimillet disable flash attention if your GPU does not support it. Here model_kwargs = dict( use_cache=False, trust_remote_code=True, attn_implementation="flash_attention_2", # loading the model with flash-attenstion support torch_dtype=torch.bfloat16, device_map=None )
0 Likes
Hello @RohanP1810, Yes, you can use Mistral models with chat completions on Azure AI services to perform RAG by combining Azure Cognitive Search for retrieval with Azure OpenAI Service for generation. This approach should leverage the strengths of both retrieval-based and generative models to provid...
0 Likes