llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from internlm2_5-7b-chat-1m-IMat-GGUF/internlm2_5-7b-chat-1m.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.name str = InternLM2 llama_model_loader: - kv 2: internlm2.context_length u32 = 262144 llama_model_loader: - kv 3: internlm2.block_count u32 = 32 llama_model_loader: - kv 4: internlm2.embedding_length u32 = 4096 llama_model_loader: - kv 5: internlm2.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: internlm2.rope.freq_base f32 = 50000000.000000 llama_model_loader: - kv 7: internlm2.attention.head_count u32 = 32 llama_model_loader: - kv 8: internlm2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 9: internlm2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 10: general.file_type u32 = 7 llama_model_loader: - kv 11: tokenizer.ggml.model str = llama llama_model_loader: - kv 12: tokenizer.ggml.pre str = default llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,92544] = ["", "~~", "~~", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,92544] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,92544] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 92542 llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q8_0: 226 tensors llm_load_vocab: special tokens cache size = 259 llm_load_vocab: token to piece cache size = 0.5531 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: n_ctx_train = 262144 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_layer = 32 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 = 4 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 = 14336 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 = 50000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 262144 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 = 7B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 7.74 B llm_load_print_meta: model size = 7.66 GiB (8.50 BPW) llm_load_print_meta: general.name = InternLM2 llm_load_print_meta: BOS token = 1 '~~' llm_load_print_meta: EOS token = 92542 '[UNUSED_TOKEN_145]' 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: 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 = 0.27 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: CPU buffer size = 384.09 MiB llm_load_tensors: CUDA0 buffer size = 7457.11 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 = 50000000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 64.00 MiB llama_new_context_with_model: KV self size = 64.00 MiB, K (f16): 32.00 MiB, V (f16): 32.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.35 MiB llama_new_context_with_model: CUDA0 compute buffer size = 188.75 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 9.01 MiB llama_new_context_with_model: graph nodes = 1030 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 103.571 ms compute_imatrix: computing over 136 chunks with batch_size 512 compute_imatrix: 0.57 seconds per pass - ETA 1.28 minutes [1]5.0346,[2]3.6723,[3]3.5707,[4]4.0879,[5]4.0274,[6]3.6532,[7]4.3100,[8]4.3760,[9]4.8143, save_imatrix: stored collected data after 10 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [10]4.9549,[11]4.5921,[12]4.9100,[13]5.5257,[14]5.8588,[15]6.3237,[16]6.5349,[17]6.2162,[18]6.4203,[19]6.7455, save_imatrix: stored collected data after 20 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [20]6.4964,[21]6.5862,[22]6.6543,[23]6.6712,[24]6.5913,[25]6.7950,[26]7.0111,[27]7.1811,[28]7.2316,[29]7.3379, save_imatrix: stored collected data after 30 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [30]7.5555,[31]7.6303,[32]7.3712,[33]7.0776,[34]6.7896,[35]6.5375,[36]6.3935,[37]6.2858,[38]6.2133,[39]6.1529, save_imatrix: stored collected data after 40 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [40]6.0788,[41]6.0151,[42]5.9126,[43]5.8695,[44]5.9202,[45]5.9750,[46]6.1160,[47]6.1016,[48]6.3090,[49]6.4878, save_imatrix: stored collected data after 50 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [50]6.6539,[51]6.7808,[52]6.9489,[53]6.8259,[54]6.9078,[55]6.9920,[56]7.1027,[57]6.9751,[58]6.9850,[59]7.0143, save_imatrix: stored collected data after 60 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [60]7.1009,[61]7.2276,[62]7.3030,[63]7.3550,[64]7.3615,[65]7.3773,[66]7.3610,[67]7.3245,[68]7.2521,[69]7.2307, save_imatrix: stored collected data after 70 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [70]7.2776,[71]7.2967,[72]7.2223,[73]7.1809,[74]7.1856,[75]7.1442,[76]7.1218,[77]7.1049,[78]7.1137,[79]7.0665, save_imatrix: stored collected data after 80 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [80]7.0704,[81]7.0205,[82]6.9936,[83]6.9500,[84]6.9328,[85]6.8774,[86]6.8457,[87]6.8165,[88]6.8428,[89]6.8503, save_imatrix: stored collected data after 90 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [90]6.8185,[91]6.8376,[92]6.8526,[93]6.8059,[94]6.7976,[95]6.7873,[96]6.8087,[97]6.8044,[98]6.8017,[99]6.7634, save_imatrix: stored collected data after 100 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [100]6.7333,[101]6.6953,[102]6.6538,[103]6.6212,[104]6.5844,[105]6.5521,[106]6.5216,[107]6.5282,[108]6.5647,[109]6.6344, save_imatrix: stored collected data after 110 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [110]6.6972,[111]6.7546,[112]6.8547,[113]6.9219,[114]6.9492,[115]6.9457,[116]6.9581,[117]6.9503,[118]6.9399,[119]6.8934, save_imatrix: stored collected data after 120 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [120]6.8699,[121]6.9023,[122]6.9007,[123]6.9027,[124]6.9205,[125]6.9609,[126]6.9884,[127]6.9980,[128]7.0215,[129]7.0489, save_imatrix: stored collected data after 130 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat [130]7.0098,[131]7.0461,[132]7.1022,[133]7.1359,[134]7.1953,[135]7.2389,[136]7.2832, save_imatrix: stored collected data after 136 chunks in internlm2_5-7b-chat-1m-IMat-GGUF/imatrix.dat llama_print_timings: load time = 1840.88 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 = 71070.73 ms / 69632 tokens ( 1.02 ms per token, 979.76 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 = 73099.32 ms / 69633 tokens Final estimate: PPL = 7.2832 +/- 0.09853