build: 5449 (8e186ef0) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu llama_model_loader: loaded meta data with 25 key-value pairs and 339 tensors from /models/Model-7.6B-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 = Model llama_model_loader: - kv 3: general.size_label str = 7.6B llama_model_loader: - kv 4: qwen2.block_count u32 = 28 llama_model_loader: - kv 5: qwen2.context_length u32 = 32768 llama_model_loader: - kv 6: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 7: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 8: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 9: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 10: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 12: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 13: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,151700] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,151700] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 151644 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 128244 llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - kv 24: 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 = 4.35 GiB (4.91 BPW) load: special tokens cache size = 58 load: token to piece cache size = 0.9313 MB print_info: arch = qwen2 print_info: vocab_only = 0 print_info: n_ctx_train = 32768 print_info: n_embd = 3584 print_info: n_layer = 28 print_info: n_head = 28 print_info: n_head_kv = 4 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 7 print_info: n_embd_k_gqa = 512 print_info: n_embd_v_gqa = 512 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: f_attn_scale = 0.0e+00 print_info: n_ff = 18944 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = -1 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 32768 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 = 7B print_info: model params = 7.61 B print_info: general.name = Model print_info: vocab type = BPE print_info: n_vocab = 151700 print_info: n_merges = 151387 print_info: BOS token = 151644 '<|im_start|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: UNK token = 128244 '' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' 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 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' 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: loading model tensors, this can take a while... (mmap = true) load_tensors: offloading 0 repeating layers to GPU load_tensors: offloaded 0/29 layers to GPU load_tensors: CPU_AARCH64 model buffer size = 2976.75 MiB load_tensors: CPU_Mapped model buffer size = 4422.31 MiB ................................................................................... llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 2048 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 0 llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized llama_context: CPU output buffer size = 0.58 MiB llama_kv_cache_unified: CPU KV buffer size = 224.00 MiB llama_kv_cache_unified: size = 224.00 MiB ( 4096 cells, 28 layers, 1 seqs), K (f16): 112.00 MiB, V (f16): 112.00 MiB llama_context: CPU compute buffer size = 303.29 MiB llama_context: graph nodes = 1098 llama_context: graph splits = 1 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) clip_ctx: CLIP using CPU backend mtmd_cli_context: chat template example: <|im_start|>system You are a helpful assistant<|im_end|> <|im_start|>user Hello<|im_end|> <|im_start|>assistant Hi there<|im_end|> <|im_start|>user How are you?<|im_end|> <|im_start|>assistant clip_model_loader: model name: clip_model_loader: description: image encoder for MiniCPM-V clip_model_loader: GGUF version: 3 clip_model_loader: alignment: 32 clip_model_loader: n_tensors: 455 clip_model_loader: n_kv: 19 load_hparams: projector: resampler load_hparams: n_embd: 1152 load_hparams: n_head: 16 load_hparams: n_ff: 4304 load_hparams: n_layer: 27 load_hparams: projection_dim: 0 load_hparams: image_size: 448 load_hparams: patch_size: 14 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 4 load_hparams: proj_scale_factor: 0 load_hparams: n_wa_pattern: 0 load_hparams: ffn_op: gelu load_hparams: model size: 996.02 MiB load_hparams: metadata size: 0.16 MiB alloc_compute_meta: CPU compute buffer size = 98.30 MiB main: loading model: /models/Model-7.6B-Q4_K_M.gguf encoding image or slice... image/slice encoded in 9826 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4417 ms encoding image or slice... image/slice encoded in 11778 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4669 ms encoding image or slice... image/slice encoded in 11286 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4807 ms encoding image or slice... image/slice encoded in 11473 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4669 ms encoding image or slice... image/slice encoded in 11529 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4966 ms encoding image or slice... image/slice encoded in 11526 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4511 ms encoding image or slice... image/slice encoded in 11520 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 5750 ms encoding image or slice... image/slice encoded in 11757 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 4580 ms encoding image or slice... image/slice encoded in 12242 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 8297 ms encoding image or slice... image/slice encoded in 17245 ms decoding image batch 1/1, n_tokens_batch = 64 image decoded (batch 1/1) in 7214 ms ```python Kroken HTR Tasks: - Compare French HTR accuracy with Finetuned TROCR. - Set up comparison logic: - Kroken - TROCR - Evaluate page segmentation performance. <--- T-C a seg - Can there models run on end-user computers? - Kroken? - TROCR? ``` llama_perf_context_print: load time = 2864.94 ms llama_perf_context_print: prompt eval time = 183669.04 ms / 755 tokens ( 243.27 ms per token, 4.11 tokens per second) llama_perf_context_print: eval time = 16542.92 ms / 78 runs ( 212.09 ms per token, 4.72 tokens per second) llama_perf_context_print: total time = 200928.48 ms / 833 tokens