Crate llama_cpp_sys
source ·Expand description
System-level, highly unsafe bindings to
llama.cpp.
There’s a lot of nuance here; for a safe alternative, see llama_cpp.
You need cmake, a compatible libc, libcxx, libcxxabi, and libclang to build this
project, along with a C/C++ compiler toolchain.
The code is automatically built for static and dynamic linking using
the cmake crate, with C FFI bindings being generated with
bindgen.
Structs§
Enums§
Constants§
Functions§
- @details Deterministically returns entire sentence constructed by a beam search. @param ctx Pointer to the llama_context. @param callback Invoked for each iteration of the beam_search loop, passing in beams_state. @param callback_data A pointer that is simply passed back to callback. @param n_beams Number of beams to use. @param n_past Number of tokens already evaluated. @param n_predict Maximum number of tokens to predict. EOS may occur earlier.
- Apply chat template. Inspired by hf apply_chat_template() on python. Both “model” and “custom_template” are optional, but at least one is required. “custom_template” has higher precedence than “model” NOTE: This function does not use a jinja parser. It only support a pre-defined list of template. See more: https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template @param tmpl A Jinja template to use for this chat. If this is nullptr, the model’s default chat template will be used instead. @param chat Pointer to a list of multiple llama_chat_message @param n_msg Number of llama_chat_message in this chat @param add_ass Whether to end the prompt with the token(s) that indicate the start of an assistant message. @param buf A buffer to hold the output formatted prompt. The recommended alloc size is 2 * (total number of characters of all messages) @param length The size of the allocated buffer @return The total number of bytes of the formatted prompt. If is it larger than the size of buffer, you may need to re-alloc it and then re-apply the template.
- @details Accepts the sampled token into the grammar
- @details Apply classifier-free guidance to the logits as described in academic paper “Stay on topic with Classifier-Free Guidance” https://arxiv.org/abs/2306.17806 @param logits Logits extracted from the original generation context. @param logits_guidance Logits extracted from a separate context from the same model. Other than a negative prompt at the beginning, it should have all generated and user input tokens copied from the main context. @param scale Guidance strength. 1.0f means no guidance. Higher values mean stronger guidance.
- @details Dynamic temperature implementation described in the paper https://arxiv.org/abs/2309.02772.
- @details Apply constraints from grammar
- @details Minimum P sampling as described in https://github.com/ggerganov/llama.cpp/pull/3841
- @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix. @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details.
- @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
- @details Tail Free Sampling described in https://www.trentonbricken.com/Tail-Free-Sampling/.
- @details Randomly selects a token from the candidates based on their probabilities.
- @details Selects the token with the highest probability. Does not compute the token probabilities. Use llama_sample_softmax() instead.
- @details Mirostat 1.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words. @param candidates A vector of
llama_token_datacontaining the candidate tokens, their probabilities (p), and log-odds (logit) for the current position in the generated text. @param tau The target cross-entropy (or surprise) value you want to achieve for the generated text. A higher value corresponds to more surprising or less predictable text, while a lower value corresponds to less surprising or more predictable text. @param eta The learning rate used to updatemubased on the error between the target and observed surprisal of the sampled word. A larger learning rate will causemuto be updated more quickly, while a smaller learning rate will result in slower updates. @param m The number of tokens considered in the estimation ofs_hat. This is an arbitrary value that is used to calculates_hat, which in turn helps to calculate the value ofk. In the paper, they usem = 100, but you can experiment with different values to see how it affects the performance of the algorithm. @param mu Maximum cross-entropy. This value is initialized to be twice the target cross-entropy (2 * tau) and is updated in the algorithm based on the error between the target and observed surprisal. - @details Mirostat 2.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words. @param candidates A vector of
llama_token_datacontaining the candidate tokens, their probabilities (p), and log-odds (logit) for the current position in the generated text. @param tau The target cross-entropy (or surprise) value you want to achieve for the generated text. A higher value corresponds to more surprising or less predictable text, while a lower value corresponds to less surprising or more predictable text. @param eta The learning rate used to updatemubased on the error between the target and observed surprisal of the sampled word. A larger learning rate will causemuto be updated more quickly, while a smaller learning rate will result in slower updates. @param mu Maximum cross-entropy. This value is initialized to be twice the target cross-entropy (2 * tau) and is updated in the algorithm based on the error between the target and observed surprisal. - @details Top-K sampling described in academic paper “The Curious Case of Neural Text Degeneration” https://arxiv.org/abs/1904.09751
- @details Nucleus sampling described in academic paper “The Curious Case of Neural Text Degeneration” https://arxiv.org/abs/1904.09751
- @details Locally Typical Sampling implementation described in the paper https://arxiv.org/abs/2202.00666.
- @details Build a split GGUF final path for this chunk. llama_split_path(split_path, sizeof(split_path), “/models/ggml-model-q4_0”, 2, 4) => split_path = “/models/ggml-model-q4_0-00002-of-00004.gguf”
- @details Extract the path prefix from the split_path if and only if the split_no and split_count match. llama_split_prefix(split_prefix, 64, “/models/ggml-model-q4_0-00002-of-00004.gguf”, 2, 4) => split_prefix = “/models/ggml-model-q4_0”
- @details Convert the provided text into tokens. @param tokens The tokens pointer must be large enough to hold the resulting tokens. @return Returns the number of tokens on success, no more than n_tokens_max @return Returns a negative number on failure - the number of tokens that would have been returned @param special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated as plaintext. Does not insert a leading space.