alexcg Profile Banner
Alex C-G Profile
Alex C-G

@alexcg

Followers
2K
Following
17K
Media
448
Statuses
7K

Open Source Evangelist and tech content writer at @jinaai_. he/him.

Berlin
Joined May 2007
Don't wanna be here? Send us removal request.
@alexcg
Alex C-G
@alexcg
5 days
RT @JinaAI_: Got a Mac with an M-chip? You can now train Gemma3 270m locally as a multilingual embedding or reranker model using our mlx-re….
0
66
0
@alexcg
Alex C-G
@alexcg
13 days
RT @JinaAI_: Two weeks ago, we released jina-embeddings-v4-GGUF with dynamic quantizations. During our experiments, we found interesting th….
0
21
0
@grok
Grok
@grok
7 days
Join millions who have switched to Grok.
193
320
2K
@alexcg
Alex C-G
@alexcg
13 days
RT @JinaAI_: Our official MCP server with read, search, embed, rerank tools on mcp[at]jina[at]ai, where we optimized the embedding and rera….
0
17
0
@alexcg
Alex C-G
@alexcg
26 days
RT @michael_g_u: Resolution is important for image embeddings - especially for visual document retrieval. jina-embeddings-v4 supports input….
Tweet card summary image
jina.ai
Image resolution is crucial for embedding visually rich documents. Too small and models miss key details; too large and they can't connect the parts.
0
2
0
@alexcg
Alex C-G
@alexcg
29 days
RT @JinaAI_: New benchmark drops: JinaVDR (Visual Document Retrieval) evals how good retrieval models handle real-world visual documents on….
0
19
0
@alexcg
Alex C-G
@alexcg
1 month
RT @JinaAI_: jina-reranker-m0-GGUF is here
Tweet card summary image
huggingface.co
0
11
0
@alexcg
Alex C-G
@alexcg
1 month
RT @JinaAI_: jina-embeddings-v4-GGUF is here with different quantizations Unsloth-like dynamic quants is on the way.
Tweet card summary image
github.com
A collection of GGUF and quantizations for jina-embeddings-v4 - jina-ai/jina-embeddings-v4-gguf
0
23
0
@alexcg
Alex C-G
@alexcg
1 month
RT @JinaAI_: Context engineering is curating the most relevant information to pack the context windows just right. Text selection and passa….
0
16
0
@alexcg
Alex C-G
@alexcg
1 month
RT @michael_g_u: We just arrived @SIGIRConf! If you're here or are interested in an internship @JinaAI_ on training the following search fo….
0
4
0
@alexcg
Alex C-G
@alexcg
2 months
RT @JinaAI_: Submodular optimization for token/sentence selection from long contexts. Here's an interesting exp: first used jina-embeddings….
0
19
0
@alexcg
Alex C-G
@alexcg
2 months
RT @JinaAI_: Many know the importance of diverse query generation in DeepResearch, but few take its implementation seriously. Most DeepRese….
0
27
0
@alexcg
Alex C-G
@alexcg
2 months
RT @jupyterjazz: I just integrated jina-embeddings-v4 with vLLM, and throughput doubled compared to inference via transformers (tested on F….
0
5
0
@alexcg
Alex C-G
@alexcg
2 months
RT @JinaAI_: Cliché is that quantization hurts performance—that you must trade quality for space. Reality? Skill issue. Learn how we traine….
0
14
0
@alexcg
Alex C-G
@alexcg
2 months
RT @JinaAI_: Today we're releasing jina-embeddings-v4, our new 3.8B universal embedding model for retrieving text, images, visual document….
0
39
0
@alexcg
Alex C-G
@alexcg
3 months
RT @JinaAI_: One interesting question people ask us is: "How do you guys vibe-check your embeddings?" Sure, there's MTEB for more serious q….
0
60
0
@alexcg
Alex C-G
@alexcg
4 months
RT @JinaAI_: Yesterday's bagging & boosting; today's model soups. It involves training multiple models with different hyperparameters or da….
0
17
0
@alexcg
Alex C-G
@alexcg
4 months
RT @JinaAI_: Size bias refers to how the length of text inputs affects similarity, regardless of semantic relevance….
Tweet card summary image
jina.ai
Size bias refers to how the length of text inputs affects similarity, regardless of semantic relevance. It explains why search systems sometimes return long, barely-relevant documents instead of...
0
10
0
@alexcg
Alex C-G
@alexcg
5 months
RT @JinaAI_: Introducing jina-reranker-m0: our new multilingual multimodal reranker model for ranking visual documents across multiple lang….
0
35
0
@alexcg
Alex C-G
@alexcg
6 months
RT @JinaAI_: Doing these 2 things right takes your DeepSearch/DeepResearch impl from mid to GOAT: (1) selecting the best snippets from leng….
0
67
0
@alexcg
Alex C-G
@alexcg
6 months
RT @JinaAI_: 4K. That's the max depth you can hide text to and embedding models can still retrieve it. Beyond that, it's gone. Using jina-e….
0
40
0