|
llama_model_loader: loaded meta data with 36 key-value pairs and 563 tensors from xLAM-8x22b-r-IMat-GGUF/xLAM-8x22b-r.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 = xLAM 8x22b R |
|
llama_model_loader: - kv 3: general.finetune str = r |
|
llama_model_loader: - kv 4: general.basename str = xLAM |
|
llama_model_loader: - kv 5: general.size_label str = 8x22B |
|
llama_model_loader: - kv 6: general.license str = cc-by-nc-4.0 |
|
llama_model_loader: - kv 7: general.tags arr[str,6] = ["function-calling", "LLM Agent", "to... |
|
llama_model_loader: - kv 8: general.languages arr[str,1] = ["en"] |
|
llama_model_loader: - kv 9: general.datasets arr[str,1] = ["Salesforce/xlam-function-calling-60k"] |
|
llama_model_loader: - kv 10: llama.block_count u32 = 56 |
|
llama_model_loader: - kv 11: llama.context_length u32 = 65536 |
|
llama_model_loader: - kv 12: llama.embedding_length u32 = 6144 |
|
llama_model_loader: - kv 13: llama.feed_forward_length u32 = 16384 |
|
llama_model_loader: - kv 14: llama.attention.head_count u32 = 48 |
|
llama_model_loader: - kv 15: llama.attention.head_count_kv u32 = 8 |
|
llama_model_loader: - kv 16: llama.rope.freq_base f32 = 1000000.000000 |
|
llama_model_loader: - kv 17: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 |
|
llama_model_loader: - kv 18: llama.expert_count u32 = 8 |
|
llama_model_loader: - kv 19: llama.expert_used_count u32 = 2 |
|
llama_model_loader: - kv 20: general.file_type u32 = 7 |
|
llama_model_loader: - kv 21: llama.vocab_size u32 = 32768 |
|
llama_model_loader: - kv 22: llama.rope.dimension_count u32 = 128 |
|
llama_model_loader: - kv 23: tokenizer.ggml.add_space_prefix bool = true |
|
llama_model_loader: - kv 24: tokenizer.ggml.model str = llama |
|
llama_model_loader: - kv 25: tokenizer.ggml.pre str = default |
|
llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,32768] = ["<unk>", "<s>", "</s>", "[INST]", "[... |
|
llama_model_loader: - kv 27: tokenizer.ggml.scores arr[f32,32768] = [-1000.000000, -1000.000000, -1000.00... |
|
llama_model_loader: - kv 28: tokenizer.ggml.token_type arr[i32,32768] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ... |
|
llama_model_loader: - kv 29: tokenizer.ggml.bos_token_id u32 = 1 |
|
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 2 |
|
llama_model_loader: - kv 31: tokenizer.ggml.unknown_token_id u32 = 0 |
|
llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false |
|
llama_model_loader: - kv 33: tokenizer.ggml.add_eos_token bool = false |
|
llama_model_loader: - kv 34: tokenizer.chat_template str = {%- if messages[0]['role'] == 'system... |
|
llama_model_loader: - kv 35: general.quantization_version u32 = 2 |
|
llama_model_loader: - type f32: 169 tensors |
|
llama_model_loader: - type q8_0: 394 tensors |
|
llm_load_vocab: special tokens cache size = 771 |
|
llm_load_vocab: token to piece cache size = 0.1731 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 = 32768 |
|
llm_load_print_meta: n_merges = 0 |
|
llm_load_print_meta: vocab_only = 0 |
|
llm_load_print_meta: n_ctx_train = 65536 |
|
llm_load_print_meta: n_embd = 6144 |
|
llm_load_print_meta: n_layer = 56 |
|
llm_load_print_meta: n_head = 48 |
|
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 = 6 |
|
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 = 16384 |
|
llm_load_print_meta: n_expert = 8 |
|
llm_load_print_meta: n_expert_used = 2 |
|
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 = 65536 |
|
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 = 8x22B |
|
llm_load_print_meta: model ftype = Q8_0 |
|
llm_load_print_meta: model params = 140.63 B |
|
llm_load_print_meta: model size = 139.17 GiB (8.50 BPW) |
|
llm_load_print_meta: general.name = xLAM 8x22b R |
|
llm_load_print_meta: BOS token = 1 '<s>' |
|
llm_load_print_meta: EOS token = 2 '</s>' |
|
llm_load_print_meta: UNK token = 0 '<unk>' |
|
llm_load_print_meta: LF token = 781 '<0x0A>' |
|
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 = 0.51 MiB |
|
llm_load_tensors: offloading 8 repeating layers to GPU |
|
llm_load_tensors: offloaded 8/57 layers to GPU |
|
llm_load_tensors: CPU buffer size = 142507.15 MiB |
|
llm_load_tensors: CUDA0 buffer size = 20299.88 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: CUDA_Host KV buffer size = 96.00 MiB |
|
llama_kv_cache_init: CUDA0 KV buffer size = 16.00 MiB |
|
llama_new_context_with_model: KV self size = 112.00 MiB, K (f16): 56.00 MiB, V (f16): 56.00 MiB |
|
llama_new_context_with_model: CUDA_Host output buffer size = 0.12 MiB |
|
llama_new_context_with_model: CUDA0 compute buffer size = 1006.25 MiB |
|
llama_new_context_with_model: CUDA_Host compute buffer size = 13.01 MiB |
|
llama_new_context_with_model: graph nodes = 2638 |
|
llama_new_context_with_model: graph splits = 580 |
|
|
|
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 95.035 ms |
|
compute_imatrix: computing over 148 chunks with batch_size 512 |
|
compute_imatrix: 22.10 seconds per pass - ETA 54.52 minutes |
|
[1]2.9422,[2]2.4068,[3]2.4574,[4]2.4981,[5]2.7972,[6]2.7795,[7]2.5772,[8]2.8890,[9]2.8177, |
|
save_imatrix: stored collected data after 10 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[10]3.1419,[11]3.2911,[12]3.1205,[13]3.3107,[14]3.5338,[15]3.8168,[16]3.9634,[17]4.1310,[18]4.2289,[19]4.2835, |
|
save_imatrix: stored collected data after 20 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[20]4.3938,[21]4.3718,[22]4.2338,[23]4.3426,[24]4.2977,[25]4.3111,[26]4.1909,[27]4.3357,[28]4.2663,[29]4.3535, |
|
save_imatrix: stored collected data after 30 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[30]4.2408,[31]4.1246,[32]3.9796,[33]3.8235,[34]3.8571,[35]3.8408,[36]3.7280,[37]3.6501,[38]3.5925,[39]3.5545, |
|
save_imatrix: stored collected data after 40 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[40]3.5272,[41]3.5403,[42]3.5236,[43]3.5163,[44]3.4834,[45]3.4681,[46]3.4927,[47]3.4854,[48]3.5567,[49]3.5861, |
|
save_imatrix: stored collected data after 50 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[50]3.5022,[51]3.4210,[52]3.3473,[53]3.2839,[54]3.2284,[55]3.2213,[56]3.2230,[57]3.2903,[58]3.3532,[59]3.3879, |
|
save_imatrix: stored collected data after 60 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[60]3.3723,[61]3.3864,[62]3.4199,[63]3.4531,[64]3.5096,[65]3.5362,[66]3.5711,[67]3.6030,[68]3.6391,[69]3.6638, |
|
save_imatrix: stored collected data after 70 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[70]3.6718,[71]3.6461,[72]3.6282,[73]3.6329,[74]3.6480,[75]3.6839,[76]3.6845,[77]3.7091,[78]3.7283,[79]3.7248, |
|
save_imatrix: stored collected data after 80 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[80]3.7290,[81]3.7231,[82]3.7408,[83]3.7569,[84]3.7644,[85]3.7800,[86]3.7807,[87]3.7861,[88]3.7842,[89]3.7976, |
|
save_imatrix: stored collected data after 90 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[90]3.7933,[91]3.7856,[92]3.7777,[93]3.7774,[94]3.7965,[95]3.8190,[96]3.8172,[97]3.8221,[98]3.8210,[99]3.8443, |
|
save_imatrix: stored collected data after 100 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[100]3.8173,[101]3.8203,[102]3.8130,[103]3.8304,[104]3.8466,[105]3.8461,[106]3.8370,[107]3.8220,[108]3.8079,[109]3.7914, |
|
save_imatrix: stored collected data after 110 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[110]3.7735,[111]3.7583,[112]3.7434,[113]3.7285,[114]3.7137,[115]3.6953,[116]3.7019,[117]3.7195,[118]3.7585,[119]3.8008, |
|
save_imatrix: stored collected data after 120 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[120]3.8363,[121]3.8893,[122]3.9339,[123]3.9424,[124]3.9539,[125]3.9356,[126]3.9345,[127]3.9310,[128]3.9347,[129]3.9020, |
|
save_imatrix: stored collected data after 130 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[130]3.8720,[131]3.8962,[132]3.9195,[133]3.9252,[134]3.9202,[135]3.9328,[136]3.9536,[137]3.9604,[138]3.9712,[139]3.9896, |
|
save_imatrix: stored collected data after 140 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
[140]4.0020,[141]4.0004,[142]3.9992,[143]3.9786,[144]3.9444,[145]3.9291,[146]3.9011,[147]3.8763,[148]3.8547, |
|
save_imatrix: stored collected data after 148 chunks in xLAM-8x22b-r-IMat-GGUF/imatrix.dat |
|
|
|
llama_print_timings: load time = 76549.47 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 = 1452198.94 ms / 75776 tokens ( 19.16 ms per token, 52.18 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 = 1507416.21 ms / 75777 tokens |
|
|
|
Final estimate: PPL = 3.8547 +/- 0.04105 |
|
|
