salamandra-2b / perplexity_IQ3_XXS.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_IQ3_XXS.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 = 23
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 iq3_xxs: 72 tensors
llama_model_loader: - type iq4_nl: 24 tensors
llama_model_loader: - type iq3_s: 25 tensors
llama_model_loader: - type iq2_s: 48 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 = IQ3_XXS - 3.0625 bpw
llm_load_print_meta: model params = 2.25 B
llm_load_print_meta: model size = 1.65 GiB (6.30 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 = 1693.41 MiB
llm_load_tensors: CPU buffer size = 214.84 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 3193.41 ms
perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1
perplexity: 12.64 seconds per pass - ETA 28.22 minutes
[1]19.2118,[2]20.0063,[3]17.8837,[4]17.7218,[5]16.7529,[6]16.1680,[7]17.1497,[8]16.6485,[9]16.2792,[10]15.4709,[11]16.2463,[12]16.3602,[13]17.5689,[14]17.8886,[15]17.8899,[16]18.4712,[17]18.8074,[18]18.7208,[19]18.7585,[20]19.0917,[21]19.0837,[22]17.2106,[23]17.3993,[24]16.9348,[25]16.3274,[26]15.8181,[27]15.5997,[28]15.3912,[29]15.3127,[30]15.0594,[31]15.3063,[32]15.4186,[33]15.9248,[34]16.2419,[35]16.5717,[36]16.3031,[37]16.2731,[38]16.3258,[39]16.1314,[40]16.1505,[41]16.1342,[42]15.9110,[43]15.8380,[44]16.0128,[45]16.2251,[46]16.0520,[47]16.3376,[48]16.4858,[49]16.8306,[50]17.1361,[51]17.1833,[52]17.4329,[53]17.7871,[54]18.1485,[55]18.2953,[56]18.1143,[57]18.0166,[58]17.7006,[59]17.5686,[60]17.3550,[61]17.3927,[62]17.5491,[63]17.7589,[64]17.8214,[65]17.8395,[66]18.0556,[67]18.0361,[68]17.9183,[69]17.7578,[70]17.6432,[71]17.6488,[72]17.5997,[73]17.6188,[74]17.5584,[75]17.5610,[76]17.4970,[77]17.5516,[78]17.5425,[79]17.5487,[80]17.5845,[81]17.2920,[82]17.2697,[83]17.1306,[84]17.1792,[85]17.2425,[86]17.4699,[87]17.5138,[88]17.6908,[89]17.7618,[90]17.8995,[91]17.9687,[92]17.7837,[93]17.8549,[94]17.8292,[95]17.9858,[96]18.2060,[97]18.2937,[98]18.4083,[99]18.5435,[100]18.5965,[101]18.6286,[102]18.5925,[103]18.5480,[104]18.5304,[105]18.5025,[106]18.3504,[107]18.2007,[108]18.2686,[109]18.2942,[110]18.1897,[111]18.1489,[112]17.9833,[113]17.8236,[114]17.8134,[115]17.7766,[116]17.7817,[117]17.6610,[118]17.5128,[119]17.5080,[120]17.5789,[121]17.6006,[122]17.6313,[123]17.6804,[124]17.7031,[125]17.7023,[126]17.7319,[127]17.7679,[128]17.8574,[129]17.8449,[130]17.8163,[131]17.8801,[132]17.8506,[133]17.7919,[134]17.6216,
Final estimate: PPL = 17.6216 +/- 0.07089
llama_perf_context_print: load time = 1210.50 ms
llama_perf_context_print: prompt eval time = 1513476.48 ms / 1097728 tokens ( 1.38 ms per token, 725.30 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 = 1570755.00 ms / 1097729 tokens
ggml_metal_free: deallocating