Error while using llama-quantize with Meta-Llama-3.1-8B-Instruct #10793
Labels
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
Name and Version
./llama-cli --version
version: 4310 (5555c0c)
built with Apple clang version 16.0.0 (clang-1600.0.26.4) for arm64-apple-darwin24.0.0
Operating systems
Mac
GGML backends
CPU
Hardware
Mac M2
Models
Meta-Llama-3.1-8B-Instruct
Problem description & steps to reproduce
Step 1
huggingface-cli login
huggingface-cli download meta-llama/Meta-Llama-3.1-8B-Instruct --local-dir Meta-Llama-3.1-8B-Instruct
Step 2
git clone https://github.com/ggerganov/llama.cpp.git
python3 -m pip install -r llama.cpp/requirements.txt
cmake -B build && cmake --build build --config Release
Step 3
python3 llama.cpp/convert_hf_to_gguf.py Meta-Llama-3.1-8B-Instruct
./llama.cpp/llama-quantize Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-8B-Instruct-F16.gguf Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-8B-Instruct--q4_0.bin q4_0
While running above Step 3 getting below error :
./llama.cpp/build/bin/llama-quantize ../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-0.06K-8b-Instruct-F16.gguf ../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-8B-Instruct--q4_0.bin q4_0
(1-ai-env) ajitw@ajit-mac tools % ./llama.cpp/build/bin/llama-quantize ../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-0.06K-8b-Instruct-F16.gguf ../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-8B-Instruct--q4_0.bin q4_0
main: build = 4310 (5555c0c)
main: built with Apple clang version 16.0.0 (clang-1600.0.26.4) for arm64-apple-darwin24.0.0
main: quantizing '../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-0.06K-8b-Instruct-F16.gguf' to '../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-8B-Instruct--q4_0.bin' as Q4_0
llama_model_loader: loaded meta data with 33 key-value pairs and 1 tensors from ../local_models/Meta-Llama-3.1-8B-Instruct/Meta-Llama-3.1-0.06K-8b-Instruct-F16.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 8B Instruct
llama_model_loader: - kv 3: general.finetune str = 8b-Instruct
llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1
llama_model_loader: - kv 5: general.size_label str = 0.06K
llama_model_loader: - kv 6: general.license str = llama3.1
llama_model_loader: - kv 7: general.base_model.count u32 = 1
llama_model_loader: - kv 8: general.base_model.0.name str = Meta Llama 3.1 8B
llama_model_loader: - kv 9: general.base_model.0.organization str = Meta Llama
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/meta-llama/Met...
llama_model_loader: - kv 11: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 12: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv 13: llama.block_count u32 = 32
llama_model_loader: - kv 14: llama.context_length u32 = 131072
llama_model_loader: - kv 15: llama.embedding_length u32 = 4096
llama_model_loader: - kv 16: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 17: llama.attention.head_count u32 = 32
llama_model_loader: - kv 18: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 19: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 20: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 21: general.file_type u32 = 1
llama_model_loader: - kv 22: llama.vocab_size u32 = 128256
llama_model_loader: - kv 23: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 25: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 29: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 31: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 32: general.quantization_version u32 = 2
llama_model_loader: - type f32: 1 tensors
/Users/ajitw/Ajit-Data/VIT/Projects/code/gen-ai-api/tools/llama.cpp/src/llama.cpp:18812: GGML_ASSERT((qs.n_attention_wv == n_attn_layer) && "n_attention_wv is unexpected") failed
zsh: abort ./llama.cpp/build/bin/llama-quantize q4_0
First Bad Commit
No response
Relevant log output
The text was updated successfully, but these errors were encountered: