llama.cpp
llama.cpp copied to clipboard
Published
2 months ago
•
ggml-org
ggml-org
Misc. bug: I'm seeing gibberish output
Name and Version
version: 4569 (2b8525d5) built with Apple clang version 16.0.0 (clang-1600.0.26.6) for x86_64-apple-darwin24.2.0
Operating systems
Mac
Which llama.cpp modules do you know to be affected?
llama-cli
Command line
./build/bin/llama-cli -m DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf
Problem description & steps to reproduce
I'm really confused (so perhaps this is not even an issue with llama.cpp per se), but I've been having issue with practically all models I have tried...
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K.gguf
DeepSeek-R1-Distill-Qwen-1.5B-Q2_K_L.gguf
DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf
DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf
DeepSeek-R1-Distill-Qwen-1.5B-Q8_0.gguf
No matter what, the output is either non-sense, or an endless string of @s (initially, I thought this was supposed to mean sth like "working"... but after minutes of wating... I concluded it's not the case lol)
Any ideas what am I doing wrong? Does it have to do with my machine or setup?
Thanks a lot in advance! 😉
First Bad Commit
No response
Relevant log output
build: 4569 (2b8525d5) with Apple clang version 16.0.0 (clang-1600.0.26.6) for x86_64-apple-darwin24.2.0
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device Metal (Intel(R) Iris(TM) Plus Graphics 655) - 1527 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 339 tensors from DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 1.5B
llama_model_loader: - kv 3: general.organization str = Deepseek Ai
llama_model_loader: - kv 4: general.basename str = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv 5: general.size_label str = 1.5B
llama_model_loader: - kv 6: qwen2.block_count u32 = 28
llama_model_loader: - kv 7: qwen2.context_length u32 = 131072
llama_model_loader: - kv 8: qwen2.embedding_length u32 = 1536
llama_model_loader: - kv 9: qwen2.feed_forward_length u32 = 8960
llama_model_loader: - kv 10: qwen2.attention.head_count u32 = 12
llama_model_loader: - kv 11: qwen2.attention.head_count_kv u32 = 2
llama_model_loader: - kv 12: qwen2.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 15: tokenizer.ggml.pre str = deepseek-r1-qwen
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - kv 26: general.file_type u32 = 15
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q4_K: 169 tensors
llama_model_loader: - type q6_K: 29 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 1.04 GiB (5.00 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch = qwen2
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 1536
print_info: n_layer = 28
print_info: n_head = 12
print_info: n_head_kv = 2
print_info: n_rot = 128
print_info: n_swa = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 6
print_info: n_embd_k_gqa = 256
print_info: n_embd_v_gqa = 256
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: n_ff = 8960
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 131072
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 1.5B
print_info: model params = 1.78 B
print_info: general.name = DeepSeek R1 Distill Qwen 1.5B
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151646 '<｜begin▁of▁sentence｜>'
print_info: EOS token = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token = 151643 '<｜end▁of▁sentence｜>'
print_info: PAD token = 151654 '<|vision_pad|>'
print_info: LF token = 148848 'ÄĬ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<｜end▁of▁sentence｜>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: offloading 28 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 29/29 layers to GPU
load_tensors: Metal_Mapped model buffer size = 1059.89 MiB
load_tensors: CPU_Mapped model buffer size = 125.19 MiB
llama_init_from_model: n_seq_max = 1
llama_init_from_model: n_ctx = 4096
llama_init_from_model: n_ctx_per_seq = 4096
llama_init_from_model: n_batch = 2048
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 0
llama_init_from_model: freq_base = 10000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
ggml_metal_init: allocating
ggml_metal_init: found device: Intel(R) Iris(TM) Plus Graphics 655
ggml_metal_init: picking default device: Intel(R) Iris(TM) Plus Graphics 655
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name: Intel(R) Iris(TM) Plus Graphics 655
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_init: simdgroup reduction = true
ggml_metal_init: simdgroup matrix mul. = false
ggml_metal_init: has residency sets = true
ggml_metal_init: has bfloat = true
ggml_metal_init: use bfloat = false
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 1610.61 MB
ggml_metal_init: skipping kernel_get_rows_bf16 (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_1row (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_f32_l4 (not supported)
ggml_metal_init: skipping kernel_mul_mv_bf16_bf16 (not supported)
ggml_metal_init: skipping kernel_mul_mv_id_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_f32_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_f16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q4_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q4_1_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q5_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q5_1_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q8_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q2_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q3_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q4_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q5_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_q6_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq2_xxs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq2_xs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq3_xxs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq3_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq2_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq1_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq1_m_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq4_nl_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_iq4_xs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_f32_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_f16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q4_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q4_1_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q5_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q5_1_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q8_0_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q2_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q3_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q4_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q5_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_q6_K_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq2_xxs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq2_xs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq3_xxs_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq3_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq2_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq1_s_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq1_m_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq4_nl_f32 (not supported)
ggml_metal_init: skipping kernel_mul_mm_id_iq4_xs_f32 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_f16_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_bf16_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_0_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q4_1_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_0_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q5_1_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h64 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h80 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h96 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h112 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_q8_0_h256 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h128 (not supported)
ggml_metal_init: skipping kernel_flash_attn_ext_vec_bf16_h256 (not supported)
ggml_metal_init: skipping kernel_cpy_f32_bf16 (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_f32 (not supported)
ggml_metal_init: skipping kernel_cpy_bf16_bf16 (not supported)
llama_kv_cache_init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1
llama_kv_cache_init: Metal KV buffer size = 112.00 MiB
llama_init_from_model: KV self size = 112.00 MiB, K (f16): 56.00 MiB, V (f16): 56.00 MiB
llama_init_from_model: CPU output buffer size = 0.58 MiB
llama_init_from_model: Metal compute buffer size = 299.75 MiB
llama_init_from_model: CPU compute buffer size = 11.01 MiB
llama_init_from_model: graph nodes = 986
llama_init_from_model: graph splits = 2
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 4
main: chat template is available, enabling conversation mode (disable it with -no-cnv)
main: chat template example:
You are a helpful assistant
<｜User｜>Hello<｜Assistant｜>Hi there<｜end▁of▁sentence｜><｜User｜>How are you?<｜Assistant｜>
system_info: n_threads = 4 (n_threads_batch = 4) / 8 | Metal : EMBED_LIBRARY = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 |
main: interactive mode on.
sampler seed: 782948815
sampler params:
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
dry_multiplier = 0.000, dry_base = 1.750, dry_allowed_length = 2, dry_penalty_last_n = 4096
top_k = 40, top_p = 0.950, min_p = 0.050, xtc_probability = 0.000, xtc_threshold = 0.100, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampler chain: logits -> logit-bias -> penalties -> dry -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
generate: n_ctx = 4096, n_batch = 2048, n_predict = -1, n_keep = 1
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to the AI.
- To return control without starting a new line, end your input with '/'.
- If you want to submit another line, end your input with '\'.
- Using default system message. To change it, set a different value via -p PROMPT or -f FILE argument.
You are a helpful assistant
> what is the capital of france?
@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
Intel macs are not well supported. Try to add -dev none to your CLI arguments - it might fix the issue.
Intel macs are not well supported. Try to add
-dev noneto your CLI arguments - it might fix the issue.
Thanks a lot for the heads-up! I'll experiment more and will let you know! 😉 🚀
I was facing the same issue since I'm on an Intel Mac.
Intel macs are not well supported. Try to add
-dev noneto your CLI arguments - it might fix the issue.
This solution fixed it for me. Thank you!
Similar problem of Qwen2.5-3B-Instruct with Q2_K on Win laptops: https://github.com/ggml-org/llama.cpp/discussions/12378
This issue was closed because it has been inactive for 14 days since being marked as stale.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}