llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from internlm2_5-7b-chat-IMat-GGUF/internlm2_5-7b-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.name str = InternLM2 llama_model_loader: - kv 2: internlm2.context_length u32 = 32768 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 = 1000000.000000 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 = 32768 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 = 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 = 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 = 1000000.0 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 125.116 ms compute_imatrix: computing over 136 chunks with batch_size 512 compute_imatrix: 1.50 seconds per pass - ETA 3.38 minutes [1]5.3660,[2]3.9648,[3]3.7793,[4]4.3816,[5]4.2898,[6]3.9196,[7]4.5676,[8]4.6225,[9]5.0903, save_imatrix: stored collected data after 10 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [10]5.2353,[11]4.8014,[12]5.1504,[13]5.7994,[14]6.1277,[15]6.6241,[16]6.8574,[17]6.5020,[18]6.7127,[19]7.0476, save_imatrix: stored collected data after 20 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [20]6.8084,[21]6.8750,[22]7.0183,[23]7.0552,[24]7.0645,[25]7.2564,[26]7.4545,[27]7.6265,[28]7.6720,[29]7.8119, save_imatrix: stored collected data after 30 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [30]8.0432,[31]8.0995,[32]7.8028,[33]7.4882,[34]7.1976,[35]6.9321,[36]6.7823,[37]6.6661,[38]6.5867,[39]6.5069, save_imatrix: stored collected data after 40 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [40]6.4153,[41]6.3593,[42]6.2493,[43]6.2304,[44]6.2903,[45]6.3623,[46]6.4987,[47]6.4758,[48]6.7113,[49]6.8952, save_imatrix: stored collected data after 50 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [50]7.0713,[51]7.1993,[52]7.3858,[53]7.2623,[54]7.3476,[55]7.4306,[56]7.5495,[57]7.4182,[58]7.4262,[59]7.4570, save_imatrix: stored collected data after 60 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [60]7.5600,[61]7.6967,[62]7.8142,[63]7.8778,[64]7.8814,[65]7.8901,[66]7.8617,[67]7.8262,[68]7.7442,[69]7.7165, save_imatrix: stored collected data after 70 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [70]7.7870,[71]7.8071,[72]7.7318,[73]7.6962,[74]7.6986,[75]7.6555,[76]7.6464,[77]7.6257,[78]7.6434,[79]7.5874, save_imatrix: stored collected data after 80 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [80]7.5887,[81]7.5350,[82]7.4994,[83]7.4532,[84]7.4326,[85]7.3718,[86]7.3389,[87]7.3023,[88]7.3406,[89]7.3531, save_imatrix: stored collected data after 90 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [90]7.3153,[91]7.3366,[92]7.3520,[93]7.3018,[94]7.2910,[95]7.2756,[96]7.3042,[97]7.3015,[98]7.3043,[99]7.2553, save_imatrix: stored collected data after 100 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [100]7.2220,[101]7.1726,[102]7.1216,[103]7.0830,[104]7.0406,[105]7.0004,[106]6.9762,[107]6.9796,[108]7.0178,[109]7.0906, save_imatrix: stored collected data after 110 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [110]7.1629,[111]7.2254,[112]7.3286,[113]7.3967,[114]7.4209,[115]7.4120,[116]7.4278,[117]7.4226,[118]7.4174,[119]7.3764, save_imatrix: stored collected data after 120 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [120]7.3639,[121]7.3932,[122]7.3968,[123]7.3999,[124]7.4179,[125]7.4566,[126]7.4840,[127]7.4967,[128]7.5167,[129]7.5438, save_imatrix: stored collected data after 130 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat [130]7.4995,[131]7.5409,[132]7.6049,[133]7.6445,[134]7.7057,[135]7.7517,[136]7.8004, save_imatrix: stored collected data after 136 chunks in internlm2_5-7b-chat-IMat-GGUF/imatrix.dat llama_print_timings: load time = 3258.43 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 = 78728.65 ms / 69632 tokens ( 1.13 ms per token, 884.46 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 = 81165.19 ms / 69633 tokens Final estimate: PPL = 7.8004 +/- 0.10722