| | batched | |
| | batched-bench | |
| | batched.swift | |
| | convert-llama2c-to-ggml | |
| | cvector-generator | |
| | deprecation-warning | |
| | embedding | |
| | eval-callback | |
| | export-lora | |
| | gbnf-validator | |
| | gen-docs | |
| | gguf | |
| | gguf-hash | |
| | gguf-split | |
| | gritlm | |
| | imatrix | |
| | infill | |
| | jeopardy | |
| | llama-bench | |
| | llama.android | |
| | llama.swiftui | |
| | llava | |
| | lookahead | |
| | lookup | |
| | main | |
| | main-cmake-pkg | |
| | parallel | |
| | passkey | |
| | perplexity | |
| | quantize | |
| | quantize-stats | |
| | retrieval | |
| | rpc | |
| | run | |
| | save-load-state | |
| | server | |
| | simple | |
| | simple-chat | |
| | speculative | |
| | speculative-simple | |
| | sycl | |
| | tokenize | |
| | chat-13B.bat | 2.4 KB |
| | chat-13B.sh | 1.3 KB |
| | chat-persistent.sh | 4.8 KB |
| | chat-vicuna.sh | 1.3 KB |
| | chat.sh | 349 B |
| | CMakeLists.txt | 1.6 KB |
| | convert_legacy_llama.py | 59.6 KB |
| | json_schema_pydantic_example.py | 3.1 KB |
| | json_schema_to_grammar.py | 32.9 KB |
| | llama.vim | 25.7 KB |
| | llm.vim | 921 B |
| | Miku.sh | 2.6 KB |
| | pydantic_models_to_grammar_examples.py | 13.4 KB |
| | pydantic_models_to_grammar.py | 54.9 KB |
| | reason-act.sh | 355 B |
| | regex_to_grammar.py | 431 B |
| | server_embd.py | 971 B |
| | server-llama2-13B.sh | 790 B |
| | ts-type-to-grammar.sh | 920 B |