llama_model_loader: loaded meta data with 30 key-value pairs and 219 tensors from internlm2_5-1_8b-chat-IMat-GGUF/internlm2_5-1_8b-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 = internlm2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Internlm2_5 1_8b Chat llama_model_loader: - kv 3: general.finetune str = chat llama_model_loader: - kv 4: general.basename str = internlm2_5 llama_model_loader: - kv 5: general.size_label str = 1.8B llama_model_loader: - kv 6: general.license str = other llama_model_loader: - kv 7: general.tags arr[str,1] = ["text-generation"] llama_model_loader: - kv 8: internlm2.context_length u32 = 32768 llama_model_loader: - kv 9: internlm2.block_count u32 = 24 llama_model_loader: - kv 10: internlm2.embedding_length u32 = 2048 llama_model_loader: - kv 11: internlm2.feed_forward_length u32 = 8192 llama_model_loader: - kv 12: internlm2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: internlm2.attention.head_count u32 = 16 llama_model_loader: - kv 14: internlm2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 15: internlm2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 16: general.file_type u32 = 7 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,92544] = ["", "~~", "~~", "<0x00>", "<... llama_model_loader: - kv 20: tokenizer.ggml.scores arr[f32,92544] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 21: tokenizer.ggml.token_type arr[i32,92544] = [3, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 22: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 92542 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 29: 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 = 9 llm_load_vocab: token to piece cache size = 0.5508 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = internlm2 llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 92544 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 32768 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 = 8 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 = 2 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 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 = 8192 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 = 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: model type = ?B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 1.89 B llm_load_print_meta: model size = 1.87 GiB (8.50 BPW) llm_load_print_meta: general.name = Internlm2_5 1_8b Chat llm_load_print_meta: BOS token = 1 '~~' llm_load_print_meta: EOS token = 92542 '<|im_end|>' llm_load_print_meta: UNK token = 0 '' llm_load_print_meta: PAD token = 2 '~~' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_print_meta: EOT token = 92542 '<|im_end|>' llm_load_print_meta: max token length = 384 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 = 192.05 MiB llm_load_tensors: CUDA0 buffer size = 1722.43 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 = 1000000.0 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 = 0.35 MiB llama_new_context_with_model: CUDA0 compute buffer size = 184.75 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 / 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 101.517 ms compute_imatrix: computing over 136 chunks with batch_size 512 compute_imatrix: 0.33 seconds per pass - ETA 0.73 minutes [1]8.1171,[2]5.9799,[3]5.7618,[4]6.6971,[5]6.4950,[6]6.0289,[7]7.0354,[8]7.1483,[9]7.7376, save_imatrix: stored collected data after 10 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [10]7.9689,[11]7.2215,[12]7.7731,[13]8.7223,[14]9.0516,[15]9.7168,[16]10.0917,[17]9.5464,[18]9.7949,[19]10.3060, save_imatrix: stored collected data after 20 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [20]9.9339,[21]9.9455,[22]10.4933,[23]10.5496,[24]10.6832,[25]11.0028,[26]11.3810,[27]11.5816,[28]11.6345,[29]11.8410, save_imatrix: stored collected data after 30 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [30]12.2061,[31]12.3618,[32]11.9333,[33]11.3946,[34]11.0039,[35]10.5436,[36]10.2947,[37]10.1431,[38]9.9996,[39]9.8758, save_imatrix: stored collected data after 40 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [40]9.6970,[41]9.6002,[42]9.4100,[43]9.4145,[44]9.5582,[45]9.6642,[46]9.8442,[47]9.7956,[48]10.1698,[49]10.4816, save_imatrix: stored collected data after 50 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [50]10.7730,[51]10.9893,[52]11.2415,[53]11.0541,[54]11.1860,[55]11.2785,[56]11.4315,[57]11.2089,[58]11.1962,[59]11.2325, save_imatrix: stored collected data after 60 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [60]11.3766,[61]11.6076,[62]11.8270,[63]11.9009,[64]11.8892,[65]11.9089,[66]11.8533,[67]11.8062,[68]11.6699,[69]11.6049, save_imatrix: stored collected data after 70 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [70]11.8227,[71]11.8646,[72]11.7587,[73]11.6955,[74]11.6992,[75]11.6129,[76]11.5900,[77]11.5655,[78]11.5782,[79]11.4525, save_imatrix: stored collected data after 80 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [80]11.4559,[81]11.3677,[82]11.3043,[83]11.2185,[84]11.1752,[85]11.0769,[86]11.0208,[87]10.9759,[88]11.0296,[89]11.0480, save_imatrix: stored collected data after 90 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [90]10.9831,[91]11.0180,[92]11.0436,[93]10.9488,[94]10.9721,[95]10.9829,[96]11.0193,[97]11.0148,[98]11.0314,[99]10.9347, save_imatrix: stored collected data after 100 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [100]10.8573,[101]10.7583,[102]10.6529,[103]10.5755,[104]10.4815,[105]10.3995,[106]10.4044,[107]10.4093,[108]10.4513,[109]10.5537, save_imatrix: stored collected data after 110 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [110]10.6555,[111]10.7395,[112]10.8834,[113]10.9967,[114]11.0452,[115]11.0187,[116]11.0439,[117]11.0456,[118]11.0526,[119]11.0112, save_imatrix: stored collected data after 120 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [120]11.0089,[121]11.0437,[122]11.0437,[123]11.0685,[124]11.0935,[125]11.1375,[126]11.1771,[127]11.1773,[128]11.1958,[129]11.2284, save_imatrix: stored collected data after 130 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat [130]11.1497,[131]11.2302,[132]11.3329,[133]11.4005,[134]11.4898,[135]11.5583,[136]11.6249, save_imatrix: stored collected data after 136 chunks in internlm2_5-1_8b-chat-IMat-GGUF/imatrix.dat llama_print_timings: load time = 951.98 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 = 27440.24 ms / 69632 tokens ( 0.39 ms per token, 2537.59 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 = 28774.74 ms / 69633 tokens Final estimate: PPL = 11.6249 +/- 0.17251