llama_model_loader: loaded meta data with 31 key-value pairs and 219 tensors from Yi-Coder-1.5B-Chat-IMat-GGUF/Yi-Coder-1.5B-Chat.Q8_0.gguf.hardlink.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 = Yi Coder 1.5B Chat llama_model_loader: - kv 3: general.finetune str = Chat llama_model_loader: - kv 4: general.basename str = Yi-Coder llama_model_loader: - kv 5: general.size_label str = 1.5B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: llama.block_count u32 = 24 llama_model_loader: - kv 8: llama.context_length u32 = 131072 llama_model_loader: - kv 9: llama.embedding_length u32 = 2048 llama_model_loader: - kv 10: llama.feed_forward_length u32 = 5504 llama_model_loader: - kv 11: llama.attention.head_count u32 = 16 llama_model_loader: - kv 12: llama.attention.head_count_kv u32 = 16 llama_model_loader: - kv 13: llama.rope.freq_base f32 = 10000000.000000 llama_model_loader: - kv 14: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 15: general.file_type u32 = 7 llama_model_loader: - kv 16: llama.vocab_size u32 = 64000 llama_model_loader: - kv 17: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 18: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 19: tokenizer.ggml.model str = llama llama_model_loader: - kv 20: tokenizer.ggml.pre str = default llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,64000] = ["", "<|startoftext|>", "<|endof... llama_model_loader: - kv 22: tokenizer.ggml.scores arr[f32,64000] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,64000] = [3, 3, 3, 3, 3, 3, 3, 3, 1, 3, 3, 3, ... llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 7 llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 28: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 29: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'... llama_model_loader: - kv 30: general.quantization_version u32 = 2 llama_model_loader: - type f32: 49 tensors llama_model_loader: - type q8_0: 170 tensors llm_load_vocab: special tokens cache size = 13 llm_load_vocab: token to piece cache size = 0.3834 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 64000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 2048 llm_load_print_meta: n_layer = 24 llm_load_print_meta: n_head = 16 llm_load_print_meta: n_head_kv = 16 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 = 1 llm_load_print_meta: n_embd_k_gqa = 2048 llm_load_print_meta: n_embd_v_gqa = 2048 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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 = 5504 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 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 = ?B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 1.48 B llm_load_print_meta: model size = 1.46 GiB (8.50 BPW) llm_load_print_meta: general.name = Yi Coder 1.5B Chat llm_load_print_meta: BOS token = 1 '<|startoftext|>' llm_load_print_meta: EOS token = 7 '<|im_end|>' llm_load_print_meta: UNK token = 0 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 315 '<0x0A>' llm_load_print_meta: EOT token = 2 '<|endoftext|>' llm_load_print_meta: max token length = 48 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes llm_load_tensors: ggml ctx size = 0.20 MiB llm_load_tensors: offloading 24 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 25/25 layers to GPU llm_load_tensors: CPU buffer size = 132.81 MiB llm_load_tensors: CUDA0 buffer size = 1363.58 MiB ..................................................................................... llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 10000000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 96.00 MiB llama_new_context_with_model: KV self size = 96.00 MiB, K (f16): 48.00 MiB, V (f16): 48.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.24 MiB llama_new_context_with_model: CUDA0 compute buffer size = 129.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 5.01 MiB llama_new_context_with_model: graph nodes = 774 llama_new_context_with_model: graph splits = 2 system_info: n_threads = 25 (n_threads_batch = 25) / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | compute_imatrix: tokenizing the input .. compute_imatrix: tokenization took 99.591 ms compute_imatrix: computing over 146 chunks with batch_size 512 compute_imatrix: 0.26 seconds per pass - ETA 0.63 minutes [1]12.3775,[2]9.0588,[3]9.6282,[4]10.7527,[5]10.4030,[6]10.8646,[7]9.4170,[8]10.3837,[9]10.3639, save_imatrix: stored collected data after 10 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [10]11.2951,[11]11.2255,[12]10.0765,[13]10.6202,[14]11.6802,[15]11.9295,[16]12.5347,[17]13.0545,[18]13.1957,[19]13.4568, save_imatrix: stored collected data after 20 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [20]14.0183,[21]13.1707,[22]12.9273,[23]13.2283,[24]13.2769,[25]13.3386,[26]12.9147,[27]13.3612,[28]13.6365,[29]14.0820, save_imatrix: stored collected data after 30 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [30]14.2418,[31]14.6417,[32]15.0781,[33]15.0261,[34]14.8378,[35]14.3335,[36]13.4314,[37]12.6496,[38]12.5749,[39]12.5084, save_imatrix: stored collected data after 40 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [40]12.4063,[41]12.0278,[42]11.6789,[43]11.4431,[44]11.1058,[45]10.8712,[46]10.8022,[47]10.9571,[48]11.1340,[49]11.3635, save_imatrix: stored collected data after 50 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [50]11.6500,[51]12.1894,[52]12.6603,[53]12.9860,[54]13.2400,[55]13.3273,[56]13.2304,[57]13.4429,[58]13.5685,[59]13.7168, save_imatrix: stored collected data after 60 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [60]13.5534,[61]13.3540,[62]13.3924,[63]13.5977,[64]13.7819,[65]13.9642,[66]14.1207,[67]14.2169,[68]14.2894,[69]14.3509, save_imatrix: stored collected data after 70 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [70]14.0953,[71]13.9685,[72]13.8202,[73]13.7003,[74]13.7496,[75]13.8581,[76]13.8593,[77]13.8964,[78]13.8617,[79]13.8240, save_imatrix: stored collected data after 80 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [80]13.7610,[81]13.6147,[82]13.6576,[83]13.6011,[84]13.5473,[85]13.5541,[86]13.4621,[87]13.3679,[88]13.2938,[89]13.2863, save_imatrix: stored collected data after 90 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [90]13.2467,[91]13.2158,[92]13.0646,[93]13.0258,[94]13.1250,[95]13.1409,[96]13.0703,[97]13.1099,[98]13.1388,[99]13.2176, save_imatrix: stored collected data after 100 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [100]13.0150,[101]13.0928,[102]13.1252,[103]13.1739,[104]13.1938,[105]13.2283,[106]13.0860,[107]12.9600,[108]12.8287,[109]12.6830, save_imatrix: stored collected data after 110 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [110]12.5595,[111]12.4451,[112]12.3245,[113]12.2095,[114]12.1711,[115]12.2043,[116]12.2625,[117]12.4031,[118]12.5382,[119]12.6627, save_imatrix: stored collected data after 120 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [120]12.8603,[121]13.0042,[122]13.0423,[123]13.0678,[124]12.9864,[125]12.9969,[126]12.9487,[127]12.8795,[128]12.7838,[129]12.7956, save_imatrix: stored collected data after 130 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [130]12.8712,[131]12.8948,[132]12.9537,[133]13.0036,[134]13.0661,[135]13.1116,[136]13.1231,[137]13.1481,[138]13.1283,[139]13.1007, save_imatrix: stored collected data after 140 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat [140]13.2059,[141]13.3078,[142]13.4163,[143]13.5452,[144]13.6686,[145]13.7820,[146]13.8676, save_imatrix: stored collected data after 146 chunks in Yi-Coder-1.5B-Chat-IMat-GGUF/imatrix.dat llama_print_timings: load time = 754.58 ms llama_print_timings: sample time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_print_timings: prompt eval time = 26818.89 ms / 74752 tokens ( 0.36 ms per token, 2787.29 tokens per second) llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_print_timings: total time = 27860.91 ms / 74753 tokens Final estimate: PPL = 13.8676 +/- 0.22522