aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-05-13embedding : remove unused code (#1426)Rinne
2023-05-13readme : update Q4_0 perplexitiesGeorgi Gerganov
I think these were affected by the removal of the `round` during quantization
2023-05-13llama : free ggml context in set / copy state data (close #1425)Georgi Gerganov
2023-05-13opencl : fix kernels for the new formats (#1422)Henri Vasserman
* Fix OpenCL kernels for the new formats * Fix Q5_0 alignment issues.
2023-05-12llama : fix --mtest option (close #1414)Georgi Gerganov
2023-05-12CLI args use - instead of _, backwards compatible (#1416)Johannes Gäßler
2023-05-12Add clang-tidy reviews to CI (#1407)slaren
2023-05-12readme : add C#/.NET bindings repo (#1409)Rinne
2023-05-12ggml : remove bit shuffling (#1405)Georgi Gerganov
* ggml : remove Q4_0 bit shufling (ARM NEON) * ggml : remove Q4_1 bit shuffling (ARM NEON + reference) * ggml : nibbles_from_floats() + bytes_from_nibbles() (ARM NEON) * ggml : remove Q4_2 bit shuffling (WIP, BROKEN) * ggml : remove Q5_0 bit shuffling (ARM NEON) * ggml : 2x faster scalar implementations * ggml : remove Q5_1 bit shuffling (ARM NEON + scalar) * ggml : simplify scalar dot * ggml : remove WASM SIMD bit shuffling + remove vzip for ARM 32-bit * ggml : fix Q4_1 quantization * ggml : update cuBLAS + normalize variable names * ggml : remove Q4_2 mode * ggml : minor formatting * ggml : fix Q5_0 quantization * scripts : add script for measuring the time per token * AVX implementations (#1370) * ggml : uniform 5th bit extraction * llama : produce error upon loading old model files * llama : fix model magic/version write * ggml : speed-up Q5_0 + Q5_1 at 4 threads * ggml : preserve old Q4 and Q5 formats * ggml : simplify Q8_1 - no need for low / high sums anymore * ggml : fix Q8_0 and Q8_1 rounding * Revert "AVX implementations (#1370)" This reverts commit 948d124837f9d287d8490f41338e0e4cceb0814f. * ggml : fix AVX2 implementation * sha : update hashes for 7B and 13B * readme : update timings + remove warning banner * llama : update v2 PR number to 1405 * ggml : fix WASM comments * ggml : back to original bit order * readme : add note that Q4 and Q5 have been changed * llama : fix return for unknown version --------- Co-authored-by: Stephan Walter <stephan@walter.name>
2023-05-11prompts : model agnostic DAN (#1304)CRD716
* add model-agnostic dan prompt * quick readme update * save a token * Revert "quick readme update" This reverts commit 8dc342c069cbdca8ce63ad974becec6fc844e1e4.
2023-05-10main : add option to save full output to session (#1338)Evan Jones
* main : add option to save full output to session * split behavior into --session and --prompt-cache * restore original implementation with new names * PR comments * move the check for incompatible parameters to gpt_params_parse * Fix whitespace Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com> --------- Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
2023-05-09Locale fix for Windows (#1379)DannyDaemonic
2023-05-09use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler (#1314)Sami Farin
* use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler Tested with a 13B model. * use _mm_pause() in busyloop * use _mm_pause() in busyloop on x86_64 to reduce power consumption
2023-05-08Interface improvements and `--multiline-input` (previously `--author-mode`) ↵DannyDaemonic
(#1040) * Interface improvements * Multiline input * Track character width * Works with all characters and control codes + Windows console fixes
2023-05-08readme : add notice about upcoming breaking changeGeorgi Gerganov
2023-05-08readme : add TOC and Pygmalion instructions (#1359)AlpinDale
2023-05-08llama : fix hparams shadow (#1367)Pavol Rusnak
fixes #1363
2023-05-08llama : require first token to be BOS (#1303)Georgi Gerganov
* llama : require first token to be BOS * scripts : add ppl-run-all.sh * perplexity : add BOS for each chunk * readme : update perplexity values after BOS fix * perplexity : add clarifying comments
2023-05-08convert: add ability to convert safetensors files (#1276)ubik2
* when loading a safetensors file, ignore the metadata header * check for safetensors files first, and only use PyTorch versions when safetensors aren't available
2023-05-08Documented CUDA reproducibility, added warning (#1346)Johannes Gäßler
2023-05-07CI: add Windows CLBlast and OpenBLAS builds (#1277)Henri Vasserman
* Add OpenCL and CLBlast support * Add OpenBLAS support * Remove testing from matrix * change build name to 'clblast'
2023-05-06ggml : Allow usage of CLBlast alongside Accelerate.framework (#1336)swittk
Minor edit in ggml.c which originally would prevent OpenCL from loading completely if GGML_USE_ACCELERATE was defined. Minor speedup in prompt eval time.
2023-05-06Remove default arguments from sampling functions (#1343)Jed Fox
2023-05-05makefile: automatic Arch Linux detection (#1332)DaniAndTheWeb
This commit is a port of a detection method used in koboldcpp's Makefile in order to automatically set the -lcblas option on Arch Linux
2023-05-05ci : add cublas to windows release (#1271)Erik Scholz
2023-05-05readme: add missing info (#1324)Pavol Rusnak
2023-05-05Fix for OpenCL / clbast builds on macOS. (#1329)Ionoclast Laboratories
2023-05-05Convert.py @staticmethod (#1327)Benjamin Lecaillon
* Line 698 has one #staticmethod and should not otherwise throw error at unpickle.load() as not callable * Update convert.py --------- Co-authored-by: Ivan Stepanov <ivanstepanovftw@gmail.com>
2023-05-05quantize: make output filename optional, default to ggml-model-<ftype>.bin ↵slaren
(#1301)
2023-05-04Wrap exceptions in std::exception to verbose output on exception. (#1316)Ivan Stepanov
2023-05-04convert: support DT_BF16 tensors (#1309)Ivan Stepanov
Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
2023-05-04readme : add OpenBuddy link (#1321)44670
2023-05-04main : add --in-suffix option (#1318)44670
* adding --in-suffix option * print input suffix before generation
2023-05-04ggml : change immintrin.h to intrin.h for compatibility (#1307)Ron Jailall
* change immintrin.h to intrin.h for compatibility Building on windows11 arm throws an error on this line. Seems like using intrin.h covers x86 and and arm * conditional def of intrin.h * fix typo in ggml.c
2023-05-04Only escape prompts when used with `-e` (#1311)DannyDaemonic
2023-05-04Update main's README.md with new features (#1296)DannyDaemonic
2023-05-04fix #1224 reverse prompt and multi line (#1297)Tomas
* fix reverse prompt and multi line * Code Formatting Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-05-03ggml : vectorize Q8_0 quantizationGeorgi Gerganov
https://github.com/ggerganov/ggml/pull/127#issuecomment-1533648531
2023-05-03examples : read chat prompts from a template file (#1196)khimaros
2023-05-03minor : fix whitespaces (#1302)Georgi Gerganov
2023-05-03minor : fix trailing whitespacesGeorgi Gerganov
2023-05-03scripts : platform independent script to verify sha256 checksums (#1203)KASR
* python script to verify the checksum of the llama models Added Python script for verifying SHA256 checksums of files in a directory, which can run on multiple platforms. Improved the formatting of the output results for better readability. * Update README.md update to the readme for improved readability and to explain the usage of the python checksum verification script * update the verification script I've extended the script based on suggestions by @prusnak The script now checks the available RAM, is there is enough to check the file at once it will do so. If not the file is read in chunks. * minor improvment small change so that the available ram is checked and not the total ram * remove the part of the code that reads the file at once if enough ram is available based on suggestions from @prusnak i removed the part of the code that checks whether the user had enough ram to read the entire model at once. the file is now always read in chunks. * Update verify-checksum-models.py quick fix to pass the git check
2023-05-03examples : various prompt and example fixes (#1298)CRD716
* fix dan.txt * miku prompt improvements * use common characters
2023-05-02llama : only copy used KV cache in get / set state (#1272)Evan Jones
* llama : only copy used KV cache in get / set state * switch to ggml for copying k, v * avoid designated initializers
2023-05-02Process escape sequences given in prompts (#1173)DannyDaemonic
2023-05-02Handle signals properly on Windows (#1123)DannyDaemonic
2023-05-02Call sh on build-info.sh (#1294)DannyDaemonic
2023-05-03fix build-info.h for git submodules (#1289)kuvaus
* make git build info work with submodules --------- Co-authored-by: Green Sky <green@g-s.xyz>
2023-05-03fix missing parameters in `llama_init_from_gpt_params` (#1293)slaren
2023-05-02examples : add llama_init_from_gpt_params() common function (#1290)Ron Evans
Signed-off-by: deadprogram <ron@hybridgroup.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-18 22:21:38 +0000