llama_model_loader: loaded meta data with 29 key-value pairs and 435 tensors from Yi-Coder-9B-IMat-GGUF/Yi-Coder-9B.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 9B llama_model_loader: - kv 3: general.basename str = Yi-Coder llama_model_loader: - kv 4: general.size_label str = 9B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: llama.block_count u32 = 48 llama_model_loader: - kv 7: llama.context_length u32 = 131072 llama_model_loader: - kv 8: llama.embedding_length u32 = 4096 llama_model_loader: - kv 9: llama.feed_forward_length u32 = 11008 llama_model_loader: - kv 10: llama.attention.head_count u32 = 32 llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 4 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000000.000000 llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 14: general.file_type u32 = 7 llama_model_loader: - kv 15: llama.vocab_size u32 = 64000 llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 17: tokenizer.ggml.model str = llama llama_model_loader: - kv 18: tokenizer.ggml.pre str = default llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,64000] = ["", "<|startoftext|>", "<|endof... llama_model_loader: - kv 20: tokenizer.ggml.scores arr[f32,64000] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 21: tokenizer.ggml.token_type arr[i32,64000] = [3, 3, 3, 3, 3, 3, 1, 1, 1, 3, 3, 3, ... llama_model_loader: - kv 22: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 23: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 24: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 97 tensors llama_model_loader: - type q8_0: 338 tensors llm_load_vocab: special tokens cache size = 11 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 = 4096 llm_load_print_meta: n_layer = 48 llm_load_print_meta: n_head = 32 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 = 8 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-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 = 11008 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 = 34B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 8.83 B llm_load_print_meta: model size = 8.74 GiB (8.50 BPW) llm_load_print_meta: general.name = Yi Coder 9B llm_load_print_meta: BOS token = 1 '<|startoftext|>' llm_load_print_meta: EOS token = 2 '<|endoftext|>' 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 = 0.41 MiB llm_load_tensors: offloading 48 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 49/49 layers to GPU llm_load_tensors: CPU buffer size = 265.62 MiB llm_load_tensors: CUDA0 buffer size = 8682.16 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 = 48.00 MiB llama_new_context_with_model: KV self size = 48.00 MiB, K (f16): 24.00 MiB, V (f16): 24.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.24 MiB llama_new_context_with_model: CUDA0 compute buffer size = 133.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 9.01 MiB llama_new_context_with_model: graph nodes = 1542 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 95.343 ms compute_imatrix: computing over 146 chunks with batch_size 512 compute_imatrix: 0.79 seconds per pass - ETA 1.90 minutes [1]7.2880,[2]5.1883,[3]5.2856,[4]5.5969,[5]5.5395,[6]5.8015,[7]4.9470,[8]5.5094,[9]5.4777, save_imatrix: stored collected data after 10 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [10]5.9434,[11]5.9764,[12]5.4793,[13]5.8090,[14]6.3599,[15]6.5982,[16]7.0200,[17]7.3588,[18]7.4586,[19]7.5772, save_imatrix: stored collected data after 20 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [20]7.8653,[21]7.5142,[22]7.4258,[23]7.5155,[24]7.5329,[25]7.5233,[26]7.2979,[27]7.5016,[28]7.6617,[29]7.9083, save_imatrix: stored collected data after 30 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [30]7.9808,[31]8.1886,[32]8.4090,[33]8.3950,[34]8.2353,[35]7.9854,[36]7.5750,[37]7.2076,[38]7.1694,[39]7.1115, save_imatrix: stored collected data after 40 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [40]7.0891,[41]6.8756,[42]6.6935,[43]6.5613,[44]6.3987,[45]6.2618,[46]6.2461,[47]6.3318,[48]6.4427,[49]6.5706, save_imatrix: stored collected data after 50 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [50]6.7226,[51]6.9875,[52]7.2196,[53]7.4019,[54]7.5350,[55]7.5759,[56]7.5082,[57]7.6188,[58]7.6928,[59]7.7780, save_imatrix: stored collected data after 60 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [60]7.7053,[61]7.6323,[62]7.6596,[63]7.7951,[64]7.9040,[65]8.0036,[66]8.0511,[67]8.1005,[68]8.1527,[69]8.1953, save_imatrix: stored collected data after 70 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [70]8.0910,[71]8.0134,[72]7.9389,[73]7.8956,[74]7.9284,[75]7.9880,[76]7.9779,[77]7.9928,[78]7.9899,[79]7.9561, save_imatrix: stored collected data after 80 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [80]7.9137,[81]7.8572,[82]7.8692,[83]7.8375,[84]7.8118,[85]7.8247,[86]7.7957,[87]7.7487,[88]7.7099,[89]7.7192, save_imatrix: stored collected data after 90 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [90]7.6908,[91]7.6689,[92]7.5977,[93]7.5844,[94]7.6399,[95]7.6387,[96]7.6007,[97]7.6168,[98]7.6299,[99]7.6494, save_imatrix: stored collected data after 100 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [100]7.5541,[101]7.6011,[102]7.6154,[103]7.6375,[104]7.6594,[105]7.6740,[106]7.6198,[107]7.5690,[108]7.5181,[109]7.4570, save_imatrix: stored collected data after 110 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [110]7.4035,[111]7.3519,[112]7.3042,[113]7.2572,[114]7.2227,[115]7.2385,[116]7.2824,[117]7.3530,[118]7.4214,[119]7.4886, save_imatrix: stored collected data after 120 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [120]7.6025,[121]7.6782,[122]7.7016,[123]7.7137,[124]7.6705,[125]7.6765,[126]7.6478,[127]7.5651,[128]7.4809,[129]7.4183, save_imatrix: stored collected data after 130 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [130]7.4634,[131]7.4627,[132]7.4897,[133]7.5171,[134]7.5629,[135]7.5906,[136]7.6044,[137]7.6149,[138]7.6157,[139]7.5994, save_imatrix: stored collected data after 140 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat [140]7.6620,[141]7.7203,[142]7.7764,[143]7.8331,[144]7.8902,[145]7.9510,[146]7.9918, save_imatrix: stored collected data after 146 chunks in Yi-Coder-9B-IMat-GGUF/imatrix.dat llama_print_timings: load time = 2336.06 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 = 108543.70 ms / 74752 tokens ( 1.45 ms per token, 688.68 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 = 110682.85 ms / 74753 tokens Final estimate: PPL = 7.9918 +/- 0.11014