imatrix.log

build: 3785 (64c6af31) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from Qwen2.5-7B-Instruct-IMat-GGUF/Qwen2.5-7B-Instruct.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 = qwen2
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen2.5 7B Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Qwen2.5
llama_model_loader: - kv 5: general.size_label str = 7B
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-7...
llama_model_loader: - kv 8: general.base_model.count u32 = 1
llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 7B
llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-7B
llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"]
llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 14: qwen2.block_count u32 = 28
llama_model_loader: - kv 15: qwen2.context_length u32 = 32768
llama_model_loader: - kv 16: qwen2.embedding_length u32 = 3584
llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 18944
llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 28
llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 4
llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 22: general.file_type u32 = 7
llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 33: general.quantization_version u32 = 2
llama_model_loader: - type f32: 141 tensors
llama_model_loader: - type q8_0: 198 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = qwen2
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 152064
llm_load_print_meta: n_merges = 151387
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 3584
llm_load_print_meta: n_layer = 28
llm_load_print_meta: n_head = 28
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 = 7
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-06
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 = 18944
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 = 2
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: 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 = 7.62 B
llm_load_print_meta: model size = 7.54 GiB (8.50 BPW) 
llm_load_print_meta: general.name = Qwen2.5 7B Instruct
llm_load_print_meta: BOS token = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token = 151645 '<|im_end|>'
llm_load_print_meta: PAD token = 151643 '<|endoftext|>'
llm_load_print_meta: LF token = 148848 'ÄĬ'
llm_load_print_meta: EOT token = 151645 '<|im_end|>'
llm_load_print_meta: max token length = 256
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 = 0.30 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors: CPU buffer size = 552.23 MiB
llm_load_tensors: CUDA0 buffer size = 7165.44 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 = 28.00 MiB
llama_new_context_with_model: KV self size = 28.00 MiB, K (f16): 14.00 MiB, V (f16): 14.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.58 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 304.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 8.01 MiB
llama_new_context_with_model: graph nodes = 986
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 | RISCV_VECT = 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 129.766 ms
compute_imatrix: computing over 128 chunks with batch_size 512
compute_imatrix: 0.65 seconds per pass - ETA 1.38 minutes
[1]5.1087,[2]3.5682,[3]3.4270,[4]3.9176,[5]3.7725,[6]3.4669,[7]3.8656,[8]3.8856,[9]4.2914,[10]4.1918,[11]4.1461,[12]4.5367,[13]5.0884,[14]5.3360,[15]5.8537,[16]6.1405,[17]6.3399,[18]6.7753,[19]6.5770,[20]6.6922,[21]6.7165,[22]6.7357,[23]6.5764,[24]6.8236,[25]7.0268,[26]6.8997,[27]6.9743,[28]6.9902,[29]7.1280,[30]7.0863,[31]6.8655,[32]6.5973,[33]6.4510,[34]6.3493,[35]6.2858,[36]6.2795,[37]6.2715,[38]6.3003,[39]6.2653,[40]6.4175,[41]6.4801,[42]6.6923,[43]6.8571,[44]7.0231,[45]7.1508,[46]7.2464,[47]7.1384,[48]7.2097,[49]7.2962,[50]7.3678,[51]7.2564,[52]7.3346,[53]7.5045,[54]7.5937,[55]7.6675,[56]7.7568,[57]7.8140,[58]7.8813,[59]7.9097,[60]7.9281,[61]7.9006,[62]7.8680,[63]7.9183,[64]7.9818,[65]7.9229,[66]7.9209,[67]7.9179,[68]7.8301,[69]7.7687,[70]7.7517,[71]7.7224,[72]7.7065,[73]7.7133,[74]7.6411,[75]7.5812,[76]7.5183,[77]7.4960,[78]7.4702,[79]7.4396,[80]7.3658,[81]7.3862,[82]7.3709,[83]7.3236,[84]7.3486,[85]7.3545,[86]7.3178,[87]7.2998,[88]7.2901,[89]7.3192,[90]7.3415,[91]7.3381,[92]7.2926,[93]7.2518,[94]7.1962,[95]7.1477,[96]7.1055,[97]7.0538,[98]7.0172,[99]6.9921,[100]6.9986,[101]7.0238,[102]7.1182,[103]7.2101,[104]7.2852,[105]7.4092,[106]7.4896,[107]7.5181,[108]7.5044,[109]7.4976,[110]7.4796,[111]7.4409,[112]7.3617,[113]7.3277,[114]7.3766,[115]7.3799,[116]7.3928,[117]7.4137,[118]7.4468,[119]7.4482,[120]7.4428,[121]7.4567,[122]7.4220,[123]7.4637,[124]7.5017,[125]7.5317,[126]7.5746,[127]7.6125,[128]7.6521,
Final estimate: PPL = 7.6521 +/- 0.11159

llama_perf_context_print: load time = 2567.57 ms
llama_perf_context_print: prompt eval time = 64306.06 ms / 65536 tokens ( 0.98 ms per token, 1019.13 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 67228.54 ms / 65537 tokens