salamandra-2b / perplexity_Q5_K_M.txt
robbiemu's picture
update for quantization
5dadba4
raw
history blame
11.1 kB
build: 3906 (7eee341b) with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.6.0
llama_model_loader: loaded meta data with 33 key-value pairs and 219 tensors from salamandra-2b_Q5_K_M.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.size_label str = 2.3B
llama_model_loader: - kv 3: general.license str = apache-2.0
llama_model_loader: - kv 4: general.tags arr[str,1] = ["text-generation"]
llama_model_loader: - kv 5: general.languages arr[str,36] = ["bg", "ca", "code", "cs", "cy", "da"...
llama_model_loader: - kv 6: llama.block_count u32 = 24
llama_model_loader: - kv 7: llama.context_length u32 = 8192
llama_model_loader: - kv 8: llama.embedding_length u32 = 2048
llama_model_loader: - kv 9: llama.feed_forward_length u32 = 5440
llama_model_loader: - kv 10: llama.attention.head_count u32 = 16
llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 16
llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 14: general.file_type u32 = 17
llama_model_loader: - kv 15: llama.vocab_size u32 = 256000
llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 17: tokenizer.ggml.add_space_prefix bool = true
llama_model_loader: - kv 18: tokenizer.ggml.model str = llama
llama_model_loader: - kv 19: tokenizer.ggml.pre str = default
llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,256000] = ["<unk>", "<s>", "</s>", "<pad>", "<|...
llama_model_loader: - kv 21: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - kv 29: quantize.imatrix.file str = imatrix/oscar/imatrix.dat
llama_model_loader: - kv 30: quantize.imatrix.dataset str = ./imatrix/oscar/imatrix-dataset.txt
llama_model_loader: - kv 31: quantize.imatrix.entries_count i32 = 168
llama_model_loader: - kv 32: quantize.imatrix.chunks_count i32 = 44176
llama_model_loader: - type f32: 49 tensors
llama_model_loader: - type q5_1: 12 tensors
llama_model_loader: - type q8_0: 12 tensors
llama_model_loader: - type q5_K: 133 tensors
llama_model_loader: - type q6_K: 12 tensors
llama_model_loader: - type bf16: 1 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 104
llm_load_vocab: token to piece cache size = 1.8842 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 = 256000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 2048
llm_load_print_meta: n_layer = 24
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
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 = 1
llm_load_print_meta: n_embd_k_gqa = 2048
llm_load_print_meta: n_embd_v_gqa = 2048
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 = 5440
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 = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 8192
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 = Q5_K - Medium
llm_load_print_meta: model params = 2.25 B
llm_load_print_meta: model size = 2.14 GiB (8.18 BPW)
llm_load_print_meta: general.name = n/a
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 = 145 '<0x0A>'
llm_load_print_meta: EOT token = 5 '<|im_end|>'
llm_load_print_meta: EOG token = 2 '</s>'
llm_load_print_meta: EOG token = 5 '<|im_end|>'
llm_load_print_meta: max token length = 72
llm_load_tensors: ggml ctx size = 0.20 MiB
llm_load_tensors: offloading 24 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 25/25 layers to GPU
llm_load_tensors: Metal buffer size = 2196.23 MiB
llm_load_tensors: CPU buffer size = 343.75 MiB
.........................................
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 128
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Max
ggml_metal_init: picking default device: Apple M3 Max
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name: Apple M3 Max
ggml_metal_init: GPU family: MTLGPUFamilyApple9 (1009)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_init: simdgroup reduction support = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 42949.67 MB
llama_kv_cache_init: Metal KV buffer size = 1536.00 MiB
llama_new_context_with_model: KV self size = 1536.00 MiB, K (f16): 768.00 MiB, V (f16): 768.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.98 MiB
llama_new_context_with_model: Metal compute buffer size = 72.00 MiB
llama_new_context_with_model: CPU compute buffer size = 125.00 MiB
llama_new_context_with_model: graph nodes = 774
llama_new_context_with_model: graph splits = 3
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 15 (n_threads_batch = 15) / 16 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 1 | SVE = 0 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 1 | LLAMAFILE = 1 |
perplexity: tokenizing the input ..
perplexity: tokenization took 2822.56 ms
perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1
perplexity: 10.90 seconds per pass - ETA 24.35 minutes
[1]15.6466,[2]15.6208,[3]14.2501,[4]14.0834,[5]13.5014,[6]13.1421,[7]13.8438,[8]13.3415,[9]13.1095,[10]12.5031,[11]13.0958,[12]13.1681,[13]14.0898,[14]14.3350,[15]14.3574,[16]14.8577,[17]15.1188,[18]15.0538,[19]15.1037,[20]15.3861,[21]15.4276,[22]13.6668,[23]13.8303,[24]13.4906,[25]13.0379,[26]12.6550,[27]12.4901,[28]12.3409,[29]12.3006,[30]12.1249,[31]12.3296,[32]12.4307,[33]12.8412,[34]13.1209,[35]13.3902,[36]13.1923,[37]13.1879,[38]13.2557,[39]13.1235,[40]13.1501,[41]13.1215,[42]12.9605,[43]12.9131,[44]13.0660,[45]13.2501,[46]13.1177,[47]13.3335,[48]13.4381,[49]13.6884,[50]13.8970,[51]13.9286,[52]14.1117,[53]14.3862,[54]14.6622,[55]14.7565,[56]14.6072,[57]14.5153,[58]14.2823,[59]14.1877,[60]14.0125,[61]14.0533,[62]14.1703,[63]14.3319,[64]14.3781,[65]14.3970,[66]14.5605,[67]14.5446,[68]14.4532,[69]14.3320,[70]14.2412,[71]14.2396,[72]14.1927,[73]14.2019,[74]14.1497,[75]14.1053,[76]14.0497,[77]14.1009,[78]14.0971,[79]14.1049,[80]14.1337,[81]13.9033,[82]13.8896,[83]13.7765,[84]13.8051,[85]13.8464,[86]14.0193,[87]14.0400,[88]14.1754,[89]14.2219,[90]14.3306,[91]14.3801,[92]14.2397,[93]14.2990,[94]14.2888,[95]14.4093,[96]14.5796,[97]14.6446,[98]14.7302,[99]14.8324,[100]14.8706,[101]14.8982,[102]14.8670,[103]14.8408,[104]14.8246,[105]14.8094,[106]14.6946,[107]14.5837,[108]14.6422,[109]14.6614,[110]14.5821,[111]14.5508,[112]14.4140,[113]14.2919,[114]14.2863,[115]14.2625,[116]14.2708,[117]14.1777,[118]14.0639,[119]14.0613,[120]14.1146,[121]14.1307,[122]14.1510,[123]14.1837,[124]14.1978,[125]14.1938,[126]14.2170,[127]14.2407,[128]14.3107,[129]14.3017,[130]14.2827,[131]14.3318,[132]14.3098,[133]14.2620,[134]14.1299,
Final estimate: PPL = 14.1299 +/- 0.05624
llama_perf_context_print: load time = 1392.57 ms
llama_perf_context_print: prompt eval time = 1558597.93 ms / 1097728 tokens ( 1.42 ms per token, 704.30 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 = 1620874.90 ms / 1097729 tokens
ggml_metal_free: deallocating