DeepSeek

@deepseek_ai1.1M followers

Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.

Open on X

Top outlier

585×

Best organic post

Peak views

12.6M

Single post

Bookmarks

58k

Across 53 organic posts

Last scan

Oct 16

Community cache

Posts 53 posts

#	Date	Post	↓ Outlier	Views	Likes	Reposts	Bookmarks
1	Jan 20, '25	🚀 DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & technical report 🏆 MIT licensed: Distill & commercialize freely! 🌐 Website &	585×	12.6M	35k	6.7k	9.6k
2	Jan 28, '25	To prevent any potential harm, we reiterate that @deepseek_ai is our sole official account on Twitter/X. Any accounts: - representing us - using identical avatars - using similar n	384×	8.2M	74k	5.8k	3.8k
3	Dec 26, '24	🚀 Introducing DeepSeek-V3! Biggest leap forward yet: ⚡ 60 tokens/second (3x faster than V2!) 💪 Enhanced capabilities 🛠 API compatibility intact 🌍 Fully open-source models &	346×	7.4M	13k	2.1k	4.9k
4	Mar 1, '25	🚀 Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview Optimized throughput and latency via: 🔧 Cross-node EP-powered batch scaling 🔄 Computation-c	186×	4M	9k	1.2k	1.7k
5	Feb 28, '25	🚀 Day 5 of #OpenSourceWeek: 3FS, Thruster for All DeepSeek Data Access Fire-Flyer File System (3FS) - a parallel file system that utilizes the full bandwidth of modern SSDs and RD	150×	3.2M	10k	1.2k	2.9k
6	Nov 20, '24	🚀 DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power! 🔍 o1-preview-level performance on AIME & MATH benchmarks. 💡 Transparent thought process in r	150×	3.2M	4.4k	771	2k
7	Feb 18, '25	🚀 Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-fast long-context training & inference! Core components of NSA: • Dynamic hierarc	122×	2.6M	15k	2k	4.4k
8	Feb 27, '25	🚀 Day 4 of #OpenSourceWeek: Optimized Parallelism Strategies ✅ DualPipe - a bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training. �	119×	2.6M	5.7k	784	794
9	Feb 21, '25	🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress w	119×	2.5M	20k	2.5k	2.1k
10	Jan 10, '25	DeepSeek has not issued any cryptocurrency. Currently, there is only one official account on the Twitter platform. We will not contact anyone through other accounts.Please stay vig	103×	2.2M	6.3k	650	412
11	Aug 21, '25	Introducing DeepSeek-V3.1: our first step toward the agent era! 🚀 🧠 Hybrid inference: Think & Non-Think — one model, two modes ⚡️ Faster thinking: DeepSeek-V3.1-Think reaches ans	97.7×	2.1M	15k	1.7k	2.6k
12	Jan 20, '25	🛠️ DeepSeek-R1: Technical Highlights 📈 Large-scale RL in post-training 🏆 Significant performance boost with minimal labeled data 🔢 Math, code, and reasoning tasks on par with O	86.4×	1.9M	4.8k	755	880
13	Feb 14, '25	🎉 Excited to see everyone’s enthusiasm for deploying DeepSeek-R1! Here are our recommended settings for the best experience: • No system prompt • Temperature: 0.6 • Official promp	85.7×	1.8M	16k	1.6k	6.2k
14	Feb 24, '25	🚀 Day 1 of #OpenSourceWeek: FlashMLA Honored to share FlashMLA - our efficient MLA decoding kernel for Hopper GPUs, optimized for variable-length sequences and now in production.	79.8×	1.7M	10k	1.3k	1.6k
15	Mar 25, '25	🚀 DeepSeek-V3-0324 is out now! 🔹 Major boost in reasoning performance 🔹 Stronger front-end development skills 🔹 Smarter tool-use capabilities ✅ For non-complex reasoning tasks,	73.1×	1.6M	12k	1.9k	1.5k
16	Jan 20, '25	📜 License Update! 🔄 DeepSeek-R1 is now MIT licensed for clear open access 🔓 Open for the community to leverage model weights & outputs 🛠️ API outputs can now be used for fi	71×	1.5M	4.7k	392	1.3k
17	May 29, '25	🚀 DeepSeek-R1-0528 is here! 🔹 Improved benchmark performance 🔹 Enhanced front-end capabilities 🔹 Reduced hallucinations 🔹 Supports JSON output & function calling ✅ Try it now:	69.6×	1.5M	9.6k	1.5k	1.4k
18	Sep 29, '25	🚀 Introducing DeepSeek-V3.2-Exp — our latest experimental model! ✨ Built on V3.1-Terminus, it debuts DeepSeek Sparse Attention(DSA) for faster, more efficient training & inference	66.4×	1.4M	6.9k	871	1.1k
19	Feb 25, '25	🚀 Day 2 of #OpenSourceWeek: DeepEP Excited to introduce DeepEP - the first open-source EP communication library for MoE model training and inference. ✅ Efficient and optimized all	64.9×	1.4M	8k	1k	1.2k
20	Jan 15, '25	🎉 Introducing DeepSeek App! 💡 Powered by world-class DeepSeek-V3 🆓 FREE to use with seamless interaction 📱 Now officially available on App Store & Google Play & Major A	64.5×	1.4M	4k	723	858
21	Jan 20, '25	🌐 API Access & Pricing ⚙️ Use DeepSeek-R1 by setting model=deepseek-reasoner 💰 $0.14 / million input tokens (cache hit) 💰 $0.55 / million input tokens (cache miss) 💰 $2.19	61.1×	1.3M	3.4k	310	559
22	Feb 26, '25	🚀 Day 3 of #OpenSourceWeek: DeepGEMM Introducing DeepGEMM - an FP8 GEMM library that supports both dense and MoE GEMMs, powering V3/R1 training and inference. ⚡ Up to 1350+ FP8 TF	45.6×	979k	6.3k	848	862
23	Jan 20, '25	🔥 Bonus: Open-Source Distilled Models! 🔬 Distilled from DeepSeek-R1, 6 small models fully open-sourced 📏 32B & 70B models on par with OpenAI-o1-mini 🤝 Empowering the open-s	41.8×	898k	3.1k	322	561
24	Feb 26, '25	🚨 Off-Peak Discounts Alert! Starting today, enjoy off-peak discounts on the DeepSeek API Platform from 16:30–00:30 UTC daily: 🔹 DeepSeek-V3 at 50% off 🔹 DeepSeek-R1 at a massive	41.8×	897k	6.5k	612	861
25	Sep 22, '25	🚀 DeepSeek-V3.1 → DeepSeek-V3.1-Terminus The latest update builds on V3.1’s strengths while addressing key user feedback. ✨ What’s improved? 🌐 Language consistency: fewer CN/EN m	39.6×	851k	4.5k	512	610
26	Dec 26, '24	💰 API Pricing Update 🎉 Until Feb 8: same as V2! 🤯 From Feb 8 onwards: Input: $0.27/million tokens ($0.07/million tokens with cache hits) Output: $1.10/million tokens 🔥 Still th	33.6×	721k	1.6k	122	274
27	Jan 15, '25	✨ Key Features of DeepSeek App: 🔐 Easy login: E-mail/Google Account/Apple ID ☁️ Cross-platform chat history sync 🔍 Web search & Deep-Think mode 📄 File upload & text extr	29.5×	634k	1.1k	119	124
28	Jan 15, '25	⚠️ Important Notice: ✅ 100% FREE - No ads, no in-app purchases 🛡️ Download only from official channels to avoid being misled 📲 Search "DeepSeek" in your app store or visit our we	25.1×	540k	1.5k	118	114
29	Jun 17, '24	DeepSeek-Coder-V2: First Open Source Model Beats GPT4-Turbo in Coding and Math > Excels in coding and math, beating GPT4-Turbo, Claude3-Opus, Gemini-1.5Pro, Codestral. > Supports 3	22.8×	490k	1.6k	323	719
30	Dec 13, '24	🎉 DeepSeek-VL2 is here! Our next-gen vision-language model enters the MoE era. 🤖 DeepSeek-MoE arch + dynamic image tilling ⚡ 3B/16B/27B sizes for flexible use 🏆 Outstanding perf	22.6×	486k	1.6k	260	459
31	Dec 26, '24	🌌 Open-source spirit + Longtermism to inclusive AGI 🌟 DeepSeek’s mission is unwavering. We’re thrilled to share our progress with the community and see the gap between open and c	21.7×	465k	1.2k	90	103
32	May 6, '24	🚀 Launching DeepSeek-V2: The Cutting-Edge Open-Source MoE Model! 🌟 Highlights: > Places top 3 in AlignBench, surpassing GPT-4 and close to GPT-4-Turbo. > Ranks top-tier in MT-Ben	19.3×	414k	995	232	495
33	Sep 29, '25	💻 API Update 🎉 Lower costs, same access! 💰 DeepSeek API prices drop 50%+, effective immediately. 🔹 For comparison testing, V3.1-Terminus remains available via a temporary API u	18.3×	394k	1.1k	93	108
34	Nov 20, '24	🌟 Inference Scaling Laws of DeepSeek-R1-Lite-Preview Longer Reasoning, Better Performance. DeepSeek-R1-Lite-Preview shows steady score improvements on AIME as thought length incre	17.4×	374k	732	85	142
35	Dec 10, '24	🚀 DeepSeek-V2.5-1210: The Grand Finale 🎉 🌐 Internet Search is now live on the web! Visit and toggle “Internet Search” for real-time answers. 🕒 🧵(1/3)	17.3×	373k	1.7k	220	501
36	Jan 28, '25	This is a typical impersonation account. Please do not trust any information from this account.	15.7×	337k	3.6k	64	39
37	Jul 18, '24	🎉Exciting news! We open-sourced DeepSeek-V2-0628 checkpoint, the No.1 open-source model on the LMSYS Chatbot Arena Leaderboard @lmsysorg. Detailed Arena Ranking: Overall No.11, Ha	14.9×	319k	766	143	191
38	Nov 20, '24	🌟 Impressive Results of DeepSeek-R1-Lite-Preview Across Benchmarks!	14.4×	310k	715	79	101
39	Feb 6, '24	🚀 DeepSeekMath: Approaching Mathematical Reasoning Capability of GPT-4 with a 7B Model. Highlights: - Continue pre-training DeepSeek-Coder-Base-v1.5 7B with 120B math tokens from	12×	257k	1k	175	652
40	Dec 13, '24	💼 Let DeepSeek-VL2 Boost Your Productivity! 🧠 Easily understand complex charts and diagrams 💻 Instantly generate plot code with precision 🧵 4/n	11.3×	242k	270	41	38
41	Sep 29, '25	🛠 Open Source Release 🔗 Model: 🔗 Tech report: 🔗 Key GPU kernels in TileLang & CUDA (use TileLang for rapid research prototyping!) 4/n	11×	237k	863	102	147
42	Oct 18, '24	🚀 Introducing Janus: a revolutionary autoregressive framework for multimodal AI! By decoupling visual encoding & unifying them with a single transformer, it outperforms previous m	10.8×	232k	917	173	396
43	Feb 5, '25	📢 Terminology Correction: DeepSeek-R1’s code and models are released under the MIT License.	10.8×	231k	862	69	32
44	Dec 13, '24	🎉 What Else Can DeepSeek-VL2 Do? 😂 Understand memes like a pro! 🔍 Identify objects from image context! 📖 Craft stories from images—let it be your storyteller! 🧵 5/n	9.9×	214k	286	34	31
45	Dec 26, '24	🎉 What’s new in V3? 🧠 671B MoE parameters 🚀 37B activated parameters 📚 Trained on 14.8T high-quality tokens 🔗 Dive deeper here: Model 👉 Paper 👉 🐋 2/n	9.6×	206k	966	78	279
46	Aug 21, '25	Tools & Agents Upgrades 🧰 📈 Better results on SWE / Terminal-Bench 🔍 Stronger multi-step reasoning for complex search tasks ⚡️ Big gains in thinking efficiency 3/5	9.1×	195k	806	46	62
47	Sep 29, '25	⚡️ Efficiency Gains 🤖 DSA achieves fine-grained sparse attention with minimal impact on output quality — boosting long-context performance & reducing compute cost. 📊 Benchmarks s	9.1×	195k	679	51	75
48	Aug 2, '24	🎉Exciting news! DeepSeek API now launches context caching on disk, with no code changes required! This new feature automatically caches frequently referenced contexts on distribut	8.9×	191k	688	125	252
49	Aug 21, '25	Model Update 🤖 🔹 V3.1 Base: 840B tokens continued pretraining for long context extension on top of V3 🔹 Tokenizer & chat template updated — new tokenizer config: 🔗 V3.1 Base Op	8.8×	189k	864	45	65
50	Aug 21, '25	Pricing Changes 💳 🔹 New pricing starts & off-peak discounts end at Sep 5th, 2025, 16:00 (UTC Time) 🔹 Until then, APIs follow current pricing 📝 Pricing page: 5/5	8.7×	186k	930	55	78
51	Dec 10, '24	📊 DeepSeek-V2.5-1210 raises the bar across benchmarks like math, coding, writing, and roleplay—built to serve all your work and life needs. 🔧 Explore the open-source model on Hug	7.9×	169k	353	45	51
52	Nov 2, '23	Introducing DeepSeek Coder! - SOTA large coding models with params ranging from 1.3B to 33B. - Building games, testing code, fixing bugs, and analyzing data... You dream it, we mak	7.8×	168k	459	98	243
53	Aug 16, '24	DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search > New SOTA: 63.5% on miniF2F (high school) & 25.3% on ProofNet (und	7.6×	163k	554	94	183
54	Sep 22, '25	📊 DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version. 👉 Available now on: App / Web / API 🔗 Open-source weights he	7.6×	163k	864	67	77
55	Sep 6, '24	🚀 Exciting news! We’ve officially launched DeepSeek-V2.5 – a powerful combination of DeepSeek-V2-0628 and DeepSeek-Coder-V2-0724! Now, with enhanced writing, instruction-following	7.3×	156k	724	125	217
56	Nov 13, '24	🚀 Introducint JanusFlow: harmonizing autoregressive LLMs with rectified flow! By adopting the best practices in both fields, JanusFlow excels at both image understanding & generat	7.1×	152k	499	92	174
57	Jul 5, '24	🚀 Introducing Expert-Specialized Fine-Tuning (ESFT) for Customizing LLMs with Sparse Architectures! 🌟 Highlights: - Train only task-relevant experts for LLM customization. - Redu	6.8×	147k	605	113	400
58	Dec 10, '24	🙌 With the release of DeepSeek-V2.5-1210, the V2 series comes to an end. 💪 Since May, the DeepSeek V2 series has brought 5 impactful updates, earning your trust and support along	6.7×	144k	324	24	21
59	Sep 18, '24	LMSYS Chatbot Arena Rankings Update: DeepSeek-V2.5 has ranked first among Chinese LLMs, outperforming closed-source models like Yi-Large-Preview, Qwen-Plus-0828, and GLM-4-0520. It	6.4×	138k	414	68	82
60	Aug 21, '25	API Update ⚙️ 🔹 deepseek-chat → non-thinking mode 🔹 deepseek-reasoner → thinking mode 🧵 128K context for both 🔌 Anthropic API format supported: ✅ Strict Function Calling suppor	6.4×	137k	790	39	99
61	Jun 21, '24	Respect to Artifacts of Claude 3.5 Sonnet! DeepSeek-Coder-V2 can do the same cool stuff directly in your browser. Visit -> select "Coder V2" -> input prompt -> click “Run HTML” to	5.1×	110k	715	126	331
62	Nov 29, '23	🚀Launching DeepSeek LLM! Next Frontier of Open-Source LLMs! #DeepSeekLLM 🧠Up to 67 billion parameters, astonishing in various benchmarks. 🔍Crafted with 2 trillion bilingual toke	5.0×	107k	383	77	193
63	Jul 10, '24	📢 After 3 months, the AI Mathematical Olympiad (AIMO) on Kaggle has announced the winners! 🎉 We're thrilled to see the Top 4 teams all chose DeepSeekMath-7B as their base model,	4.6×	99k	640	99	157
64	Jan 11, '24	🌟 Meet #DeepSeekMoE: The Next Gen of Large Language Models! Performance Highlights: 📈 DeepSeekMoE 2B matches its 2B dense counterpart with 17.5% computation. 🚀 DeepSeekMoE 16B r	4.6×	99k	380	77	198
65	Jul 4, '24	DeepSeek API Now Supports 128K Context Length at 32K Pricing. Access the API at: #DeepSeek #DeepSeekAPI	4.5×	97k	343	52	77
66	May 6, '24	DeepSeek-V2 is a strong, economical, and efficient MoE language model, enhanced with exceptional architectural designs in attention mechanisms and sparse layers: 🌟 MLA (Multi-head	4.2×	91k	181	20	93
67	Nov 3, '23	🚀 DeepSeek Coder 33B is NOW LIVE! Open-source & absolutely FREE! #DeepSeekCoder 💥 Try out here: 🤗 Also on Huggingface: 💬 Got questions? Join our Discord fam! 🤖 Github page	4.0×	85k	189	45	68
68	May 6, '24	> Chat with DeepSeek-V2: > Access pay-as-you-go DeepSeek-V2 APIs with unbeatable price: > DeepSeek-V2 is fully open-source and free for commercial use:	3.9×	85k	221	39	135
69	Aug 29, '24	🚀 Just published: "Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts" 🌐 Introducing Loss-Free Balancing—our latest innovation in MoE models that ditches the need	3.9×	84k	377	64	125
70	Jun 17, '24	> Chat with DeepSeek-Coder-V2 (230B) : > Access Coder-V2 APIs at the same unbeatable prices as DeepSeek-V2: > Download two-sized models for free commercial/research use: > Technica	3.7×	79k	167	28	112
71	Jul 23, '24	We're hiring AI researchers & engineers, AI tutors & product, data & infra. Find more：	3.6×	78k	283	42	85
72	Sep 18, '24	Compared to DeepSeek-V2 and DeepSeek-Coder-V2, DeepSeek V2.5 has seen comprehensive improvements in rankings across all categories.	3.6×	77k	104	17	6
73	Sep 6, '24	In our internal Chinese evaluations, DeepSeek-V2.5 shows a significant improvement in win rates against GPT-4o mini and ChatGPT-4o-latest (judged by GPT-4o) compared to DeepSeek-V2	3.2×	69k	122	20	15
74	Sep 6, '24	DeepSeek-V2.5 is now open-source on HuggingFace! Check it out:	2.9×	62k	169	20	35
75	May 17, '24	🔥 Last week, the release and buzz around DeepSeek-V2 have ignited widespread interest in MLA (Multi-head Latent Attention)! Many in the community suggested open-sourcing a smaller	2.9×	62k	285	51	105
76	Jun 17, '24	In the Arena-Hard-Auto leaderboard, DeepSeek-Coder-V2 surpasses Yi-large,Claude3-Opus, GLM4, and Qwen2-72B.	2.6×	56k	144	10	26
77	Jul 26, '24	🚀 DeepSeek API Update! 🚀 🌟 New Features (for deepseek-coder & deepseek-chat): /chat/completions: - JSON Mode - Function Calling - Chat Prefix Completion (Beta) - 8K max_tokens (	2.6×	56k	235	47	38
78	Sep 6, '24	DeepSeek-V2.5 outperforms both DeepSeek-V2-0628 and DeepSeek-Coder-V2-0724 on most benchmarks.	2.4×	53k	75	5	7
79	Dec 18, '23	🎉 We're proud to release the code for our latest 3D generation work, "DreamCraft3D". Check it out from ➡️ which has exceeded 1.4k stars on GitHub 🚀🔥. #DeepSeekAI #3DGeneration #	2.4×	51k	251	67	139
80	Mar 12, '24	[1/5] 🚀 Announcing DeepSeek-VL, sota 1.3B and 7B visual-language models! Paper: GitHub: 📚 Diverse training corpus 👯 Hybrid Vision Encoder 🧠 3-stage training strategy 🆓 Totally	2.4×	51k	320	63	158
81	Aug 29, '24	To be specific, before the top-K routing decision, Loss-Free Balancing will first apply an expert-wise bias to the routing scores of each expert. By dynamically updating the bias o	2.3×	49k	83	12	17
82	Jun 21, '24	DeepSeek-Coder-V2 can develop awesome mini-games directly in your browser.	1.8×	40k	154	17	37
83	Jan 26, '24	🚀 Just Out: Tech Report On #DeepSeekCoder - An Open-Source Model Competing with #GPT4's Coding Capabilities. Paper Link: ⭐ Highlights: - Repo-level Data Construction - Topological	1.8×	39k	172	36	69
84	Jan 26, '24	🚀Trying out the new code model: DeepSeek-Coder-v1.5-7B. It's built upon DeepSeek-LLM-7B with an additional 1.4T Tokens of code data. 📈 DeepSeek-Coder-v1.5 steps up in natural lan	1.5×	32k	56	8	13
85	Apr 25, '24	🎉 Starting today, the DeepSeek APIs offer pay-as-you-go options at attractive low prices! ✨ Sign up for 5M free tokens. Want more? Purchase 1M tokens for only $0.14 to $0.28! 👉 K	1.4×	31k	102	15	45
86	Nov 8, '23	🎉🎉 Thrilled to announce that our DeepSeek-Coder's official repo has clinched the top spot in GitHub's Python trending! 📈🐍 Plus, we're the runner-up in the overall GitHub trendi	1.3×	28k	59	9	10
87	Jun 21, '24	DeepSeek-Coder-V2 can craft dynamic websites directly in your browser.	1.3×	27k	80	3	19
88	Jan 8, '24	📚Out Now: Technical Report on DeepSeek LLM 67B! Read more: 🔍Discover our in-depth study on scaling laws and how data quality influences them. ✨In the MT-Bench evaluation, DeepSee	1.1×	24k	150	36	59
89	Nov 2, '23	Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks including HumanEval, MultiPL-E, MBPP, DS	1.1×	24k	59	3	11
90	Nov 4, '23	🚀 Good news! In addition to our official site 🎉, our 7B/33B models are also available for a quick taste on @huggingface Space! Curious? Experience them now🤗: 7B: 33B:	1.1×	23k	59	10	15
91	Apr 9, '24	🔥 AIMO on Kaggle: $1M+ in prizes for AI math solvers! 🧠 DeepSeekMath model is leading the charge, but we need more brilliant minds! 🤖Think you can create an AI that out-maths th	1.0×	21k	58	8	12
92	Feb 1, '24	🚀 DeepSeek now with APIs! Drop in replacement for OpenAI. Free tokens available.	0.9×	20k	92	17	26
93	Dec 13, '24	💡 Still Fully Open-Source! Come explore our model and check out the code—technical report coming soon! 💾 Hugging Face: 💻 Github Page: 🧵 2/n	0.9×	19k	89	9	28
94	Dec 13, '24	🔧 Technical Improvements 📊 Data: 2x high-quality training data vs. DeepSeek-VL1, unlocking new capabilities 🏗️ Architecture: Dynamic image tiling for flexible resolutions + effi	0.9×	19k	57	4	4
95	Oct 30, '23	🚀 Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:	0.9×	19k	81	15	34
96	Nov 29, '23	👀 Never Seen Before Exam 🎓 Excelled in the Hungarian National High-School Exam. 📝 Tops in Google's Instruction Following Evaluation. 🖥️ Outstanding performance in LeetCode Week	0.6×	14k	43	8	7
97	Jan 11, '24	Finetune Code: Download Model: Paper Preview：	0.6×	13k	43	3	15
98	Nov 29, '23	🤗 Discover our models on Huggingface: 💬 Join our Discord fam for lively discussions! 🤖 Explore more details on our Github repo:	0.6×	12k	45	3	11
99	Nov 2, '23	- Massive Training Data: Trained on 2T tokens, including 86 programming languages. - Highly Flexible & Scalable: Offered in model sizes of 1B, 5.7B, 6.7B and 33B. - Advanced Co	0.6×	12k	45	2	8

Scan another creator

Run this on any account.

XOutlier builds this table for every public profile you open on x.com, with live data and every post, not just the top 50.

Add to Chrome Download .zip