Qwen VL - how can I not output logs other than the model's response?

[prt0117]

Hello Dear Community!

I am trying to use the Qwen VL, but I cannot suppress the output of logs before and after the model's response. For example, the following command

`./build/bin/llama-qwen2vl-cli -m ./models/Qwen2-VL-7B-Instruct-Q4_0.gguf --mmproj ./models/mmproj-Qwen2-VL-7B-Instruct-f32.gguf -p 'Describe this image.' --image './models/test_image.jpg'`

outputs:

build: 4383 (485dc012) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
llama_model_loader: loaded meta data with 37 key-value pairs and 339 tensors from ./models/Qwen2-VL-7B-Instruct-Q4_0.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              = qwen2vl
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2 VL 7B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2-VL
llama_model_loader: - kv   5:                         general.size_label str              = 7B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                   general.base_model.count u32              = 1
llama_model_loader: - kv   8:                  general.base_model.0.name str              = Qwen2 VL 7B
llama_model_loader: - kv   9:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  10:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2-VL-7B
llama_model_loader: - kv  11:                               general.tags arr[str,2]       = ["multimodal", "image-text-to-text"]
llama_model_loader: - kv  12:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  13:                        qwen2vl.block_count u32              = 28
llama_model_loader: - kv  14:                     qwen2vl.context_length u32              = 32768
llama_model_loader: - kv  15:                   qwen2vl.embedding_length u32              = 3584
llama_model_loader: - kv  16:                qwen2vl.feed_forward_length u32              = 18944
llama_model_loader: - kv  17:               qwen2vl.attention.head_count u32              = 28
llama_model_loader: - kv  18:            qwen2vl.attention.head_count_kv u32              = 4
llama_model_loader: - kv  19:                     qwen2vl.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  20:   qwen2vl.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  21:                          general.file_type u32              = 2
llama_model_loader: - kv  22:            qwen2vl.rope.dimension_sections arr[i32,4]       = [16, 24, 24, 0]
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {% set image_count = namespace(value=...
llama_model_loader: - kv  32:               general.quantization_version u32              = 2
llama_model_loader: - kv  33:                      quantize.imatrix.file str              = /models_out/Qwen2-VL-7B-Instruct-GGUF...
llama_model_loader: - kv  34:                   quantize.imatrix.dataset str              = /training_dir/calibration_datav3.txt
llama_model_loader: - kv  35:             quantize.imatrix.entries_count i32              = 196
llama_model_loader: - kv  36:              quantize.imatrix.chunks_count i32              = 128
llama_model_loader: - type  f32:  141 tensors
llama_model_loader: - type q4_0:  194 tensors
llama_model_loader: - type q4_1:    3 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: special tokens cache size = 14
llm_load_vocab: token to piece cache size = 0.9309 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2vl
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 3584
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 28
llm_load_print_meta: n_head_kv        = 4
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 7
llm_load_print_meta: n_embd_k_gqa     = 512
llm_load_print_meta: n_embd_v_gqa     = 512
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 18944
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 8
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 7.62 B
llm_load_print_meta: model size       = 4.13 GiB (4.66 BPW) 
llm_load_print_meta: general.name     = Qwen2 VL 7B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: max token length = 256
llm_load_tensors:   CPU_Mapped model buffer size =  4196.14 MiB
llm_load_tensors:  CPU_AARCH64 model buffer size =  3391.17 MiB
......................................................................................
clip_model_load: model name:   Qwen2-VL-7B-Instruct
clip_model_load: description:  image encoder for Qwen2VL
clip_model_load: GGUF version: 3
clip_model_load: alignment:    32
clip_model_load: n_tensors:    521
clip_model_load: n_kv:         20
clip_model_load: ftype:        f32

clip_model_load: loaded meta data with 20 key-value pairs and 521 tensors from ./models/mmproj-Qwen2-VL-7B-Instruct-f32.gguf
clip_model_load: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
clip_model_load: - kv   0:                       general.architecture str              = clip
clip_model_load: - kv   1:                        general.description str              = image encoder for Qwen2VL
clip_model_load: - kv   2:                          general.file_type u32              = 0
clip_model_load: - kv   3:                      clip.has_text_encoder bool             = false
clip_model_load: - kv   4:                    clip.has_vision_encoder bool             = true
clip_model_load: - kv   5:                    clip.has_qwen2vl_merger bool             = true
clip_model_load: - kv   6:                        clip.projector_type str              = qwen2vl_merger
clip_model_load: - kv   7:                              clip.use_silu bool             = false
clip_model_load: - kv   8:                              clip.use_gelu bool             = false
clip_model_load: - kv   9:                     clip.vision.patch_size u32              = 14
clip_model_load: - kv  10:                     clip.vision.image_size u32              = 560
clip_model_load: - kv  11:               clip.vision.embedding_length u32              = 1280
clip_model_load: - kv  12:                 clip.vision.projection_dim u32              = 3584
clip_model_load: - kv  13:           clip.vision.attention.head_count u32              = 16
clip_model_load: - kv  14:   clip.vision.attention.layer_norm_epsilon f32              = 0.000001
clip_model_load: - kv  15:                    clip.vision.block_count u32              = 32
clip_model_load: - kv  16:            clip.vision.feed_forward_length u32              = 0
clip_model_load: - kv  17:                               general.name str              = Qwen2-VL-7B-Instruct
clip_model_load: - kv  18:                     clip.vision.image_mean arr[f32,3]       = [0.481455, 0.457828, 0.408211]
clip_model_load: - kv  19:                      clip.vision.image_std arr[f32,3]       = [0.268630, 0.261303, 0.275777]
clip_model_load: - type  f32:  521 tensors
clip_model_load: CLIP using CPU backend
clip_model_load: text_encoder:   0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector:  0
clip_model_load: minicpmv_projector:  0
clip_model_load: model size:     2577.82 MB
clip_model_load: metadata size:  0.18 MB
clip_model_load: params backend buffer size =  2577.82 MB (521 tensors)
key clip.vision.image_grid_pinpoints not found in file
key clip.vision.mm_patch_merge_type not found in file
key clip.vision.image_crop_resolution not found in file
clip_model_load: compute allocated memory: 198.93 MB
llama_new_context_with_model: n_seq_max     = 1
llama_new_context_with_model: n_ctx         = 4096
llama_new_context_with_model: n_ctx_per_seq = 4096
llama_new_context_with_model: n_batch       = 2048
llama_new_context_with_model: n_ubatch      = 512
llama_new_context_with_model: flash_attn    = 0
llama_new_context_with_model: freq_base     = 1000000.0
llama_new_context_with_model: freq_scale    = 1
llama_new_context_with_model: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 28
llama_kv_cache_init:        CPU KV buffer size =   224.00 MiB
llama_new_context_with_model: KV self size  =  224.00 MiB, K (f16):  112.00 MiB, V (f16):  112.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.58 MiB
llama_new_context_with_model:        CPU compute buffer size =   304.00 MiB
llama_new_context_with_model: graph nodes  = 986
llama_new_context_with_model: graph splits = 1
encode_image_with_clip: step 1 of 1 encoded in 71298.16 ms
encode_image_with_clip: all 1 segments encoded in 71298.19 ms
encode_image_with_clip: load_image_size 958 539
encode_image_with_clip: image embedding created: 700 tokens

Then it outputs the response:

The image depicts a street scene where two individuals appear to be...

And then it outputs a little more logs:

llama_perf_context_print:        load time =  135007.65 ms
llama_perf_context_print: prompt eval time =   58405.58 ms /   725 tokens (   80.56 ms per token,    12.41 tokens per second)
llama_perf_context_print:        eval time =   47276.63 ms /   255 runs   (  185.40 ms per token,     5.39 tokens per second)
llama_perf_context_print:       total time =  182521.68 ms /   980 tokens

Could you please help me to disable everything around the response so that it only writes to the terminal:

The image depicts a street scene where two individuals appear to be...

I was trying --log-disable and 2>/dev/null but it didn't help.

Thank you in advance!

[samkoesnadi]

Try adding -lv -100 to your cmd prompt. It is to set log level, above the defined value will be ignored. So, info etc are not shown. Mind me asking you what you use Qwen2 VL for, I am working also on it.

[samkoesnadi]

Correction apparently, using -lv will remove all of the output. Perhaps modifying the log output in the llama.cpp file is the only way.

[prt0117]

Hello. Thank you for the information. I was trying to use Qwen2 VL for video understanding experiments.

[samkoesnadi]

Hello. Thank you for the information. I was trying to use Qwen2 VL for video understanding experiments.

Sounds great!