mac studio : loading model vocabulary: unknown pre-tokenizer type: 'grok-2'
#5
by
cloudyu
- opened
llama_model_loader: - type f32: 321 tensors
llama_model_loader: - type q8_0: 128 tensors
llama_model_loader: - type q4_K: 385 tensors
llama_model_loader: - type q5_K: 64 tensors
llama_model_loader: - type q6_K: 65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 152.78 GiB (4.87 BPW)
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'grok-2'
./llama-cli --version
version: 6455 (d032a1b09)
built with Apple clang version 17.0.0 (clang-1700.0.13.3) for arm64-apple-darwin24.5.0
on mac studio I have pull the last llama.cpp and build successfully
git fetch origin pull/15539/head:MASTER && git checkout MASTER && cd ..
From https://github.com/ggerganov/llama.cpp
- [new ref] refs/pull/15539/head -> MASTER
M .github/workflows/build.yml
M .github/workflows/release.yml
M CONTRIBUTING.md
M ci/run.sh
M common/arg.cpp
M common/common.h
M convert_hf_to_gguf.py
M convert_hf_to_gguf_update.py
M docs/backend/CANN.md
M docs/build-s390x.md
M docs/ops.md
M docs/ops/zDNN.csv
M examples/eval-callback/eval-callback.cpp
M examples/model-conversion/requirements.txt
M examples/model-conversion/scripts/causal/run-org-model.py
M ggml/include/ggml-backend.h
M ggml/include/ggml-metal.h
M ggml/include/ggml-zdnn.h
M ggml/src/ggml-backend-impl.h
M ggml/src/ggml-backend-reg.cpp
M ggml/src/ggml-cann/aclnn_ops.cpp
M ggml/src/ggml-cann/common.h
M ggml/src/ggml-cann/ggml-cann.cpp
M ggml/src/ggml-cpu/CMakeLists.txt
M ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
M ggml/src/ggml-cpu/ops.cpp
M ggml/src/ggml-cuda/CMakeLists.txt
M ggml/src/ggml-cuda/binbcast.cu
M ggml/src/ggml-cuda/common.cuh
M ggml/src/ggml-cuda/fattn-tile.cu
M ggml/src/ggml-cuda/getrows.cu
M ggml/src/ggml-cuda/ggml-cuda.cu
M ggml/src/ggml-cuda/mma.cuh
M ggml/src/ggml-cuda/mmf.cu
M ggml/src/ggml-cuda/mmf.cuh
M ggml/src/ggml-cuda/template-instances/generate_cu_files.py
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_1.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_10.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_11.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_12.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_13.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_14.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_15.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_16.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_2.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_3.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_4.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_5.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_6.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_7.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_8.cu
A ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_9.cu
M ggml/src/ggml-cuda/vendors/hip.h
M ggml/src/ggml-metal/CMakeLists.txt
A ggml/src/ggml-metal/ggml-metal-common.cpp
A ggml/src/ggml-metal/ggml-metal-common.h
M ggml/src/ggml-metal/ggml-metal.m
M ggml/src/ggml-metal/ggml-metal.metal
M ggml/src/ggml-sycl/binbcast.cpp
M ggml/src/ggml-sycl/concat.cpp
M ggml/src/ggml-sycl/conv.cpp
M ggml/src/ggml-sycl/convert.cpp
M ggml/src/ggml-sycl/cpy.cpp
M ggml/src/ggml-sycl/dmmv.cpp
M ggml/src/ggml-sycl/dpct/helper.hpp
M ggml/src/ggml-sycl/element_wise.cpp
M ggml/src/ggml-sycl/getrows.cpp
M ggml/src/ggml-sycl/ggml-sycl.cpp
M ggml/src/ggml-sycl/gla.cpp
M ggml/src/ggml-sycl/im2col.cpp
M ggml/src/ggml-sycl/mmq.cpp
M ggml/src/ggml-sycl/mmvq.cpp
M ggml/src/ggml-sycl/norm.cpp
M ggml/src/ggml-sycl/rope.cpp
M ggml/src/ggml-sycl/set_rows.cpp
M ggml/src/ggml-sycl/softmax.cpp
M ggml/src/ggml-sycl/tsembd.cpp
M ggml/src/ggml-sycl/wkv.cpp
M ggml/src/ggml-vulkan/ggml-vulkan.cpp
M ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_s.comp
M ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_xxs.comp
M ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_s.comp
M ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_xxs.comp
M ggml/src/ggml-vulkan/vulkan-shaders/soft_max_back.comp
M ggml/src/ggml-zdnn/ggml-zdnn-impl.h
M ggml/src/ggml-zdnn/ggml-zdnn.cpp
M gguf-py/gguf/constants.py
M gguf-py/gguf/gguf_writer.py
M gguf-py/gguf/tensor_mapping.py
A media/llama1-icon-transparent.png
A media/llama1-icon-transparent.svg
M requirements/requirements-convert_hf_to_gguf.txt
M requirements/requirements-convert_legacy_llama.txt
M requirements/requirements-tool_bench.txt
M src/llama-arch.cpp
M src/llama-arch.h
M src/llama-chat.cpp
M src/llama-chat.h
M src/llama-context.cpp
M src/llama-graph.cpp
M src/llama-hparams.h
M src/llama-model.cpp
M src/llama-quant.cpp
M src/llama-vocab.cpp
M src/llama-vocab.h
M src/llama.cpp
M tests/.gitignore
M tests/test-backend-ops.cpp
M tests/test-tokenizer-random.py
M tools/llama-bench/llama-bench.cpp
M tools/main/README.md
M tools/mtmd/clip.cpp
M tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py
M tools/mtmd/requirements.txt
M tools/rpc/rpc-server.cpp
M tools/server/server.cpp
M tools/server/tests/requirements.txt
Switched to branch 'MASTER'