llama.cpp aarch64 619ff883f66482f6046c468fc315d2611809e982d6c32104609dba2900c04402

Port of English lagre model LLaMA implemented based on C/C++

Port of English lagre model LLaMA implemented based on C/C++, it can be used for model dialogue based on local laptops. https://github.com/ggerganov/llama.cpp MIT openEuler Copr - user zwjsec2 Unspecified eur-prod-workerlocal-aarch64-normal-prod-00438144-20241106-1250 llama.cpp-20241102-2.src.rpm /usr/bin/llama-baby-llama /usr/bin/llama-batched /usr/bin/llama-batched-bench /usr/bin/llama-bench /usr/bin/llama-cli /usr/bin/llama-convert-llama2c-to-ggml /usr/bin/llama-cvector-generator /usr/bin/llama-embedding /usr/bin/llama-eval-callback /usr/bin/llama-export-lora /usr/bin/llama-gbnf-validator /usr/bin/llama-gguf /usr/bin/llama-gguf-hash /usr/bin/llama-gguf-split /usr/bin/llama-gritlm /usr/bin/llama-imatrix /usr/bin/llama-infill /usr/bin/llama-llava-cli /usr/bin/llama-lookahead /usr/bin/llama-lookup /usr/bin/llama-lookup-create /usr/bin/llama-lookup-merge /usr/bin/llama-lookup-stats /usr/bin/llama-minicpmv-cli /usr/bin/llama-parallel /usr/bin/llama-passkey /usr/bin/llama-perplexity /usr/bin/llama-quantize /usr/bin/llama-quantize-stats /usr/bin/llama-retrieval /usr/bin/llama-save-load-state /usr/bin/llama-server /usr/bin/llama-simple /usr/bin/llama-simple-chat /usr/bin/llama-speculative /usr/bin/llama-tokenize /usr/bin/llama_convert_hf_to_gguf.py /usr/bin/test-arg-parser /usr/bin/test-autorelease /usr/bin/test-backend-ops /usr/bin/test-barrier /usr/bin/test-chat-template /usr/bin/test-grad0 /usr/bin/test-grammar-integration /usr/bin/test-grammar-parser /usr/bin/test-json-schema-to-grammar /usr/bin/test-llama-grammar /usr/bin/test-log /usr/bin/test-model-load-cancel /usr/bin/test-quantize-fns /usr/bin/test-quantize-perf /usr/bin/test-rope /usr/bin/test-sampling /usr/bin/test-tokenizer-0 /usr/bin/test-tokenizer-1-bpe /usr/bin/test-tokenizer-1-spm llama.cpp src 8134b3c99acef5c188d2e041a933dcf13fe9fae36e8ccf143ed5d6925184d27a

Port of English lagre model LLaMA implemented based on C/C++

Port of English lagre model LLaMA implemented based on C/C++, it can be used for model dialogue based on local laptops. https://github.com/ggerganov/llama.cpp MIT openEuler Copr - user zwjsec2 Unspecified eur-prod-workerlocal-aarch64-normal-prod-00438144-20241106-1250