Make my experimental branch support Mixtral #4
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
happens with multi-threaded quantization of Qwen-72B ggml-ci
* enable qwen to llama.cpp * llama : do not GPU split bias tensors --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Support attention_bias on LLaMA architecture QKVO bias, should fix InternLM (ggml-org#3133) and works for LLaMAfied Qwen models (ggml-org#3743 (comment)). * check existence of qkvo bias while loading llama models Tested on LLaMA2, CUDA and CPU. * Update llama.cpp
* Fix token_to_piece implementation in Swift * Fix errors
* llama : pad KV cache size to 32 * metal : try to improve batched decoding
(cherry picked from commit mozilla-ai/llamafile@e8c92bc)
This reverts commit a8e66ef.
# Conflicts: # CMakeLists.txt # Makefile
* ggml : fix soft max out-of-bounds access ggml-ci * ggml : reuse ggml_get_n_tasks() in ggml_graph_plan() ggml-ci
preceeding -> preceding
This commit updates the error message that is printed when the KV cache is not big enough to hold all the prompt and generated tokens. Specifically it removes the reference to n_parallel and replaces it with n_len. Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
* Samplers sequence order w parameter * Cleaned commented code * Fixed formatting * Rewrote with unordered_map * Revert and rewrite, too many problems and safeguards would be needed * Fixed code style * Code style fixes according to review * More readable samplers input string, fixed help * Style fix in sampler_queue * Formatting fixes * Fixing whitespaces
) * feat: Allow overriding GGUF metadata when loading model * Fix the one time GCC is stricter than clang about something * Step1 * Refactor... basically everything! * Nuke obsolete GetArrayLen struct * simplify std::string specialization * Various cleanups Add informational output when overrides are applied Warn user when an override with the wrong type is specified * Fix broken logic for parsing bool KV overrides Fix issue where overrides didn't apply when key missing in GGUF metadata Resolve merge changes * llama : rearrange model params * Update new GET_KEY call Add note that metadata KV overrides aren't reflected in initial metadata KV info dump --------- Co-authored-by: cebtenzzre <cebtenzzre@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
…l-org#4330) * reserve space for codepoints * improvement for the appended 0 * used precomputed token text for grammar sample * reserve canidates_decoded * reserve canidates_grammar * remove candidates_decoded * Revert "remove candidates_decoded" This reverts commit 3773328. * changed decode_utf8 to take src by ref
* speculative: add some colors * minor : add braces --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Set a more typical Top P setting as the default * Update temp max
# Conflicts: # Makefile # tests/test-grad0.cpp # tests/test-quantize-perf.cpp
* convert : support Mixtral as LLAMA arch * convert : fix n_ff typo * llama : model loading * ggml : sync latest ggml_mul_mat_id * llama : update graph to support MoE * llama : fix cur -> cur_expert * llama : first working version * llama : fix expert weighting in the FFN * ggml : ggml_get_rows support 2D indexing [n_tokens, n_experts] (cpu only) * ggml : add n_as argument to ggml_mul_mat_id * ggml : fix ggml_get_rows to take into account ne02 / ne11 * metal : add more general support for ggml_get_rows + tests * llama : add basic support for offloading moe with CUDA * metal : add/mul/div use general kernel when src1 not cont * metal : reduce the kernel launches for ggml_mul_mat_id * ggml : get_rows : support non-contiguos tensors with gaps, generalize up to 3D * ggml : update get_rows f16 and q * cuda : support non-contiguous src1 in get_rows * llama : offload missing ffn_moe_silu * metal : fix ggml_get_rows to work with non-cont src1 * metal : add indirect mat-vec kernels for all quantization types * llama : do not quantize expert gating tensors * llama : add n_expert and n_expert_used to hparams + change quants * test-backend-ops : add moe test * cuda : fix get_rows when ncols is odd * convert : determine n_ctx correctly * metal : fix ggml_mul_mat_id for F32 * test-backend-ops : make experts more evenly probable (test_moe) * test-backend-ops : cleanup, add moe test for batches * test-backend-ops : add cpy from f32 -> all types test * test-backend-ops : fix dequantize block offset * llama : fix hard-coded number of experts * test-backend-ops : simplify and disable slow tests to avoid CI timeout * test-backend-ops : disable MOE test with thread sanitizer * cuda : fix mul_mat_id with multi gpu * convert : use 1e6 rope_freq_base for mixtral * convert : fix style * convert : support safetensors format * gguf-py : bump version * metal : add cpy f16 -> f32 kernel * metal : fix binary ops for ne10 % 4 != 0 * test-backend-ops : add one more sum_rows test * ggml : do not use BLAS with ggml_mul_mat_id * convert-hf : support for mixtral-instruct (ggml-org#4428) * convert : typo fix, add additional hyperparameters, use LLaMA arch for Mixtral-instruct * convert : use sentencepiece tokenizer for Mixtral-instruct * convert : make flake8 happy * metal : fix soft_max kernels ref: ggml-org/ggml@1914017 * metal : limit kernels to not use more than the allowed threads --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Radek Pilar <github@mrkva.eu>
# Conflicts: # Makefile # README.md
* .sh script V1 * koboldcpp.sh polish * koboldcpp.sh dist generator * Include html's in dist * RWKV in Linux Dist * Lower dependency requirements * Eliminate wget dependency * More distinct binary name I know its technically amd64, but I don't want to cause confusion among nvidia users. * Use System OpenCL Unsure how this will behave in the pyinstaller build, but pocl ended up CPU only. With a bit of luck the pyinstaller uses the one from the actual system if compiled in a system without opencl, while conda now includes it for that specific system. * Add cblas dependency Missing this causes compile failures on some system's * ICD workaround Ideally we find a better solution, but conda forces ICD and needs this for the successful compile. However, pyinstaller then embeds the ICD causing it to be limited to the system it was compiled for. By temporarily removing the ICD pyinstaller can't find it and everything remains functional. Ideally we do this on a pyinstaller level, but I could not find any good options to do so yet. * Fix & Nocuda --------- Co-authored-by: root <root@DESKTOP-DQ1QRAG>
* sync : ggml (SD ops, tests, kernels) ggml-ci * cuda : restore im2col ggml-ci * metal : fix accuracy of dequantization kernels ggml-ci * cuda : restore correct im2col ggml-ci * metal : try to fix moe test by reducing expert size ggml-ci * cuda : fix bin bcast when src1 and dst have different types ggml-ci --------- Co-authored-by: slaren <slarengh@gmail.com>
* .sh script V1 * koboldcpp.sh polish * koboldcpp.sh dist generator * Include html's in dist * RWKV in Linux Dist * Lower dependency requirements * Eliminate wget dependency * More distinct binary name I know its technically amd64, but I don't want to cause confusion among nvidia users. * Use System OpenCL Unsure how this will behave in the pyinstaller build, but pocl ended up CPU only. With a bit of luck the pyinstaller uses the one from the actual system if compiled in a system without opencl, while conda now includes it for that specific system. * Add cblas dependency Missing this causes compile failures on some system's * ICD workaround Ideally we find a better solution, but conda forces ICD and needs this for the successful compile. However, pyinstaller then embeds the ICD causing it to be limited to the system it was compiled for. By temporarily removing the ICD pyinstaller can't find it and everything remains functional. Ideally we do this on a pyinstaller level, but I could not find any good options to do so yet. * Fix & Nocuda * Automatically build Linux Binary * Auto build on v tag * Better on release * Fix missing jobs: * More distinct name * I am to retro... * Fix release upload * Another upload attempt * Another upload attempt * Also rebuild on release edit * Placebo commit to maybe fix CI --------- Co-authored-by: root <root@DESKTOP-DQ1QRAG>
This reverts commit 7a69152.
…certain models, which seems to be caused by some imprecision related to the automatic casting of floating point values
…3633) * Add HFVocab into convert.py * Update convert.py * Update convert.py * add bytes_to_unicode function * change add_meta_vocab fucntion * remove debug code * remove byte_encoder * Add newline between classes * Check tokenizer.json when tokenizer.model is not exist. * Move transformers dependency to local code * Add error context with 'raise from' * Add fast tokenizer option to BpeVocab * Update convert.py * Add VocabLoader and remove *Vocab class * Add transformers dependency * remove added tokens and check newline token to decide spm or bpe * Update convert.py * Add special token type * Update convert.py * Update convert.py * Update convert.py * Fix typo in convert.py * Fix when params.n_vocab < tokenizer vocab size * update vocab class * change funtion name * Remove unused variable/functions, add types to class variable and methods, delete blank liens * fix flake8 warnings * code style cleanup * make mypy happy * change exception --------- Co-authored-by: Jared Van Bortel <jared@nomic.ai>
…certain models, which seems to be caused by some imprecision related to the automatic casting of floating point values (cherry picked from commit 1ad8f0d)
# Conflicts: # CMakeLists.txt # Makefile # README.md
…ered on certain models, which seems to be caused by some imprecision related to the automatic casting of floating point values" This reverts commit 34b3dac.
# Conflicts: # ggml.c
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
nuff said