Résultats plein texte:

ai_agent

10 Occurrences trouvées, Dernière modification : il y a 6 jours

ng-ai-riding-an-llphant-an-open-source-library-to-use-llms-and-vector-dbs-in-php/272059145#1|Exploring AI riding an LLPhant - An Open Source Library to use LLMs and vector DBs in PHP]] (slide, juillet 2023... nteractions avec l'utilisateur ''clarify'', ''ask_user''. ===== À quoi ça sert ? ===== ==== Agent de... oment * ... ^ Agent ^ Github ⭐ ^ Primary use ^ | Agent Zero | 17.2k | General-purpose autonomo

ai_coding

6 Occurrences trouvées, Dernière modification : il y a 6 jours

4, n_embd=2048, n_rot=128, n_expert=128, n_expert_used=8, n_vocab=151936, n_merges=151387, max token le... oken length=256, n_rot=128, n_expert=64, n_expert_used=6 * RTX 3060 12 Go * ''<nowiki>--c... it's interconnected, constantly evolving ; Cline use AST (Abstract Syntax Tree) Listes d'agents * [... conversation : "Conversation roles must alternate user/assistant/user..." ==== cline ==== * https:/

mcp-inspector

5 Occurrences trouvées, Dernière modification : il y a 12 jours

27.0.0.1:6274,http://localhost:6274" \ -v /home/user/dev/mbox-mcp:/mcp \ -v /home/user/dev/mbox-mcp/data:/mcp-data \ cyrille37/mcp-inspector </code> ... e projet Php+composer est dans le dossier ''/home/user/dev/mbox-mcp''. * Le point d'entrée sur mcp est ''/home/user/dev/mbox-mcp/bin/mbox-mcp.php'' * Les datas né

ai_vision

4 Occurrences trouvées, Dernière modification : il y a 7 semaines

.pt'' sur 1521 tuiles de 640 pixels: ^ ^ real ^ user ^ sys ^ | CUDA RTX 3060 | 0m25,625s | 0m22,140s ... ec CPU i7-1360P 13thGen real 0m47,583s, 0m32,031s user 0m0,112s, 0m0,110s sys 0m0,025s, 0m0,025s Avec RTX 3060 real 0m5,929s, 0m3,367s user 0m0,099s, 0m0,104s sys 0m0,027s, 0m0,027s </code... mproj-F16.gguf -ngl 20 real 0m39,938s, 0m45,901s user 0m0,116s, 0m0,105s sys 0m0,024s, 0m0,027s </code

gpu_bench

4 Occurrences trouvées, Dernière modification : il y a 17 heures

t_info: n_expert = 0 print_info: n_expert_used = 0 print_info: n_expert_groups = 0 print_info: n_group_used = 0 print_info: causal attn = 1 print_i... n_threads_batch = 4) / 24 | CUDA : ARCHS = 1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | BLACKWEL... 5060 Ti): 49 layers (24 overflowing), 14678 MiB used, 1034 MiB free common_fit_params: successfully

ai_nlp_rag

3 Occurrences trouvées, Dernière modification : il y a 6 jours

of milliseconds. * One of the easiest ways to use ColBERT in applications nowadays is the semi-offi... LLM generates a more abstract query; both queries used for retrieval across all tree levels - Confide... tence Transformers ===== https://www.sbert.net/ used to compute embeddings using Sentence Transformer