File size: 10,666 Bytes
4f2836a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from llm-compiler-7b-IMat-GGUF/llm-compiler-7b.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.name str = llm-compiler-7b
llama_model_loader: - kv 2: llama.block_count u32 = 32
llama_model_loader: - kv 3: llama.context_length u32 = 16384
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 32
llama_model_loader: - kv 8: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 7
llama_model_loader: - kv 11: llama.vocab_size u32 = 32000
llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
llama_model_loader: - kv 14: tokenizer.ggml.pre str = default
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 22: tokenizer.ggml.add_eos_token bool = false
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 = 0.1684 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 = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 16384
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 4096
llm_load_print_meta: n_embd_v_gqa = 4096
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 = 11008
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 = 16384
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 = 6.74 B
llm_load_print_meta: model size = 6.67 GiB (8.50 BPW)
llm_load_print_meta: general.name = llm-compiler-7b
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 = 13 '<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 = 0.27 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 = 132.81 MiB
llm_load_tensors: CUDA0 buffer size = 6695.84 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 = 256.00 MiB
llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.12 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 70.50 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 98.047 ms
compute_imatrix: computing over 151 chunks with batch_size 512
compute_imatrix: 0.59 seconds per pass - ETA 1.47 minutes
[1]6.6836,[2]5.1025,[3]5.0990,[4]6.0509,[5]6.8286,[6]6.9178,[7]6.4531,[8]7.0779,[9]7.2172,
save_imatrix: stored collected data after 10 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[10]7.6626,[11]7.6180,[12]6.7697,[13]6.6368,[14]6.9780,[15]7.4385,[16]7.5302,[17]7.8579,[18]8.0717,[19]8.2099,
save_imatrix: stored collected data after 20 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[20]8.3085,[21]8.5583,[22]8.1441,[23]7.7425,[24]7.8041,[25]7.8916,[26]7.8419,[27]7.6914,[28]7.8043,[29]7.9600,
save_imatrix: stored collected data after 30 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[30]8.0985,[31]8.1050,[32]8.2265,[33]8.3044,[34]8.5184,[35]8.5777,[36]8.4893,[37]8.1221,[38]7.8718,[39]7.7932,
save_imatrix: stored collected data after 40 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[40]7.7251,[41]7.6244,[42]7.5451,[43]7.3857,[44]7.2989,[45]7.2049,[46]7.1984,[47]7.2254,[48]7.2786,[49]7.3786,
save_imatrix: stored collected data after 50 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[50]7.3834,[51]7.5855,[52]7.7687,[53]7.9564,[54]8.1367,[55]8.2275,[56]8.1763,[57]8.1040,[58]8.1407,[59]8.2010,
save_imatrix: stored collected data after 60 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[60]8.2955,[61]8.1878,[62]8.2123,[63]8.2870,[64]8.3726,[65]8.4340,[66]8.4646,[67]8.5276,[68]8.5576,[69]8.5352,
save_imatrix: stored collected data after 70 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[70]8.5404,[71]8.5466,[72]8.4782,[73]8.4271,[74]8.3748,[75]8.3548,[76]8.3520,[77]8.3590,[78]8.3342,[79]8.3392,
save_imatrix: stored collected data after 80 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[80]8.3615,[81]8.3437,[82]8.3309,[83]8.2756,[84]8.2916,[85]8.2987,[86]8.2900,[87]8.3182,[88]8.3145,[89]8.3015,
save_imatrix: stored collected data after 90 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[90]8.2822,[91]8.2930,[92]8.2448,[93]8.2390,[94]8.2104,[95]8.1747,[96]8.1994,[97]8.1919,[98]8.2019,[99]8.1808,
save_imatrix: stored collected data after 100 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[100]8.1697,[101]8.1935,[102]8.1551,[103]8.1190,[104]8.1010,[105]8.1276,[106]8.1249,[107]8.1380,[108]8.1674,[109]8.0909,
save_imatrix: stored collected data after 110 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[110]8.0305,[111]7.9669,[112]7.9005,[113]7.8343,[114]7.7723,[115]7.7137,[116]7.6576,[117]7.6158,[118]7.6329,[119]7.6453,
save_imatrix: stored collected data after 120 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[120]7.6954,[121]7.7506,[122]7.8016,[123]7.8576,[124]7.9541,[125]8.0482,[126]8.0601,[127]8.0794,[128]8.0077,[129]8.0114,
save_imatrix: stored collected data after 130 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[130]7.9939,[131]7.9857,[132]7.9606,[133]7.9555,[134]7.9690,[135]7.9940,[136]7.9830,[137]7.9785,[138]7.9913,[139]8.0043,
save_imatrix: stored collected data after 140 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[140]8.0231,[141]8.0263,[142]8.0282,[143]8.0130,[144]7.9915,[145]8.0111,[146]8.0400,[147]8.0742,[148]8.1063,[149]8.1451,
save_imatrix: stored collected data after 150 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
[150]8.1810,[151]8.2203,
save_imatrix: stored collected data after 151 chunks in llm-compiler-7b-IMat-GGUF/imatrix.dat
llama_print_timings: load time = 1857.95 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 = 81192.92 ms / 77312 tokens ( 1.05 ms per token, 952.20 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 = 82973.02 ms / 77313 tokens
Final estimate: PPL = 8.2203 +/- 0.10580
|