|
|
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no |
|
|
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no |
|
|
ggml_cuda_init: found 2 CUDA devices: |
|
|
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes |
|
|
Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes |
|
|
build: 7040 (92bb442ad) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu |
|
|
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) (0000:01:00.0) - 19489 MiB free |
|
|
llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) (0000:03:00.0) - 23060 MiB free |
|
|
llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from /mnt/world8/AI/ToBench/Seed-OSS-36B-Instruct-unsloth/Magic_Quant/GGUF/Seed-OSS-36B-Instruct-unsloth-BF16.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 = seed_oss |
|
|
llama_model_loader: - kv 1: general.type str = model |
|
|
llama_model_loader: - kv 2: general.name str = Seed OSS 36B Instruct Unsloth |
|
|
llama_model_loader: - kv 3: general.finetune str = Instruct-unsloth |
|
|
llama_model_loader: - kv 4: general.basename str = Seed-OSS |
|
|
llama_model_loader: - kv 5: general.size_label str = 36B |
|
|
llama_model_loader: - kv 6: general.license str = apache-2.0 |
|
|
llama_model_loader: - kv 7: general.base_model.count u32 = 1 |
|
|
llama_model_loader: - kv 8: general.base_model.0.name str = Seed OSS 36B Instruct |
|
|
llama_model_loader: - kv 9: general.base_model.0.organization str = ByteDance Seed |
|
|
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/ByteDance-Seed... |
|
|
llama_model_loader: - kv 11: general.tags arr[str,3] = ["vllm", "unsloth", "text-generation"] |
|
|
llama_model_loader: - kv 12: seed_oss.block_count u32 = 64 |
|
|
llama_model_loader: - kv 13: seed_oss.context_length u32 = 524288 |
|
|
llama_model_loader: - kv 14: seed_oss.embedding_length u32 = 5120 |
|
|
llama_model_loader: - kv 15: seed_oss.feed_forward_length u32 = 27648 |
|
|
llama_model_loader: - kv 16: seed_oss.attention.head_count u32 = 80 |
|
|
llama_model_loader: - kv 17: seed_oss.attention.head_count_kv u32 = 8 |
|
|
llama_model_loader: - kv 18: seed_oss.rope.freq_base f32 = 10000000.000000 |
|
|
llama_model_loader: - kv 19: seed_oss.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
|
llama_model_loader: - kv 20: seed_oss.attention.key_length u32 = 128 |
|
|
llama_model_loader: - kv 21: seed_oss.attention.value_length u32 = 128 |
|
|
llama_model_loader: - kv 22: general.file_type u32 = 32 |
|
|
llama_model_loader: - kv 23: general.quantization_version u32 = 2 |
|
|
llama_model_loader: - kv 24: tokenizer.ggml.model str = gpt2 |
|
|
llama_model_loader: - kv 25: tokenizer.ggml.pre str = seed-coder |
|
|
llama_model_loader: - kv 26: tokenizer.ggml.tokens arr[str,155136] = ["<seed:bos>", "<seed:pad>", "<seed:e... |
|
|
llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,155136] = [3, 3, 3, 4, 4, 4, 4, 4, 4, 3, 3, 3, ... |
|
|
llama_model_loader: - kv 28: tokenizer.ggml.merges arr[str,154737] = ["Ġ Ġ", "Ġ t", "i n", "Ġ a", "e r... |
|
|
llama_model_loader: - kv 29: tokenizer.ggml.bos_token_id u32 = 0 |
|
|
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 2 |
|
|
llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 1 |
|
|
llama_model_loader: - kv 32: tokenizer.chat_template str = {# Unsloth Chat template fixes #}\n{# ... |
|
|
llama_model_loader: - type f32: 321 tensors |
|
|
llama_model_loader: - type bf16: 450 tensors |
|
|
print_info: file format = GGUF V3 (latest) |
|
|
print_info: file type = BF16 |
|
|
print_info: file size = 67.34 GiB (16.00 BPW) |
|
|
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect |
|
|
load: printing all EOG tokens: |
|
|
load: - 2 ('<seed:eos>') |
|
|
load: special tokens cache size = 128 |
|
|
load: token to piece cache size = 0.9296 MB |
|
|
print_info: arch = seed_oss |
|
|
print_info: vocab_only = 0 |
|
|
print_info: n_ctx_train = 524288 |
|
|
print_info: n_embd = 5120 |
|
|
print_info: n_embd_inp = 5120 |
|
|
print_info: n_layer = 64 |
|
|
print_info: n_head = 80 |
|
|
print_info: n_head_kv = 8 |
|
|
print_info: n_rot = 128 |
|
|
print_info: n_swa = 0 |
|
|
print_info: is_swa_any = 0 |
|
|
print_info: n_embd_head_k = 128 |
|
|
print_info: n_embd_head_v = 128 |
|
|
print_info: n_gqa = 10 |
|
|
print_info: n_embd_k_gqa = 1024 |
|
|
print_info: n_embd_v_gqa = 1024 |
|
|
print_info: f_norm_eps = 0.0e+00 |
|
|
print_info: f_norm_rms_eps = 1.0e-06 |
|
|
print_info: f_clamp_kqv = 0.0e+00 |
|
|
print_info: f_max_alibi_bias = 0.0e+00 |
|
|
print_info: f_logit_scale = 0.0e+00 |
|
|
print_info: f_attn_scale = 0.0e+00 |
|
|
print_info: n_ff = 27648 |
|
|
print_info: n_expert = 0 |
|
|
print_info: n_expert_used = 0 |
|
|
print_info: n_expert_groups = 0 |
|
|
print_info: n_group_used = 0 |
|
|
print_info: causal attn = 1 |
|
|
print_info: pooling type = 0 |
|
|
print_info: rope type = 2 |
|
|
print_info: rope scaling = linear |
|
|
print_info: freq_base_train = 10000000.0 |
|
|
print_info: freq_scale_train = 1 |
|
|
print_info: n_ctx_orig_yarn = 524288 |
|
|
print_info: rope_finetuned = unknown |
|
|
print_info: model type = 36B |
|
|
print_info: model params = 36.15 B |
|
|
print_info: general.name = Seed OSS 36B Instruct Unsloth |
|
|
print_info: vocab type = BPE |
|
|
print_info: n_vocab = 155136 |
|
|
print_info: n_merges = 154737 |
|
|
print_info: BOS token = 0 '<seed:bos>' |
|
|
print_info: EOS token = 2 '<seed:eos>' |
|
|
print_info: PAD token = 1 '<seed:pad>' |
|
|
print_info: LF token = 326 'Ċ' |
|
|
print_info: EOG token = 2 '<seed:eos>' |
|
|
print_info: max token length = 1024 |
|
|
load_tensors: loading model tensors, this can take a while... (mmap = true) |
|
|
load_tensors: offloading 20 repeating layers to GPU |
|
|
load_tensors: offloaded 20/65 layers to GPU |
|
|
load_tensors: CPU_Mapped model buffer size = 68955.52 MiB |
|
|
load_tensors: CUDA0 model buffer size = 10300.86 MiB |
|
|
load_tensors: CUDA1 model buffer size = 10300.86 MiB |
|
|
.................................................................................................. |
|
|
llama_context: constructing llama_context |
|
|
llama_context: n_seq_max = 1 |
|
|
llama_context: n_ctx = 2048 |
|
|
llama_context: n_ctx_seq = 2048 |
|
|
llama_context: n_batch = 2048 |
|
|
llama_context: n_ubatch = 512 |
|
|
llama_context: causal_attn = 1 |
|
|
llama_context: flash_attn = auto |
|
|
llama_context: kv_unified = false |
|
|
llama_context: freq_base = 10000000.0 |
|
|
llama_context: freq_scale = 1 |
|
|
llama_context: n_ctx_seq (2048) < n_ctx_train (524288) -- the full capacity of the model will not be utilized |
|
|
llama_context: CPU output buffer size = 0.59 MiB |
|
|
llama_kv_cache: CPU KV buffer size = 352.00 MiB |
|
|
llama_kv_cache: CUDA0 KV buffer size = 80.00 MiB |
|
|
llama_kv_cache: CUDA1 KV buffer size = 80.00 MiB |
|
|
llama_kv_cache: size = 512.00 MiB ( 2048 cells, 64 layers, 1/1 seqs), K (f16): 256.00 MiB, V (f16): 256.00 MiB |
|
|
llama_context: Flash Attention was auto, set to enabled |
|
|
llama_context: CUDA0 compute buffer size = 1828.00 MiB |
|
|
llama_context: CUDA1 compute buffer size = 194.01 MiB |
|
|
llama_context: CUDA_Host compute buffer size = 14.01 MiB |
|
|
llama_context: graph nodes = 2183 |
|
|
llama_context: graph splits = 621 (with bs=512), 4 (with bs=1) |
|
|
common_init_from_params: added <seed:eos> logit bias = -inf |
|
|
common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048 |
|
|
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) |
|
|
|
|
|
system_info: n_threads = 16 (n_threads_batch = 16) / 32 | CUDA : ARCHS = 860 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | |
|
|
perplexity: tokenizing the input .. |
|
|
perplexity: tokenization took 121.448 ms |
|
|
perplexity: calculating perplexity over 48 chunks, n_ctx=2048, batch_size=2048, n_seq=1 |
|
|
perplexity: 18.10 seconds per pass - ETA 14.48 minutes |
|
|
[1]1.5107,[2]1.4416,[3]1.2762,[4]1.2238,[5]1.1809,[6]1.2685,[7]1.3738,[8]1.4318,[9]1.4155,[10]1.3932,[11]1.3715,[12]1.3774,[13]1.3779,[14]1.3640,[15]1.3454,[16]1.3621,[17]1.3633,[18]1.3450,[19]1.3424,[20]1.3583,[21]1.3485,[22]1.3382,[23]1.3488,[24]1.3431,[25]1.3473,[26]1.3431,[27]1.3609,[28]1.3662,[29]1.3668,[30]1.3675,[31]1.3649,[32]1.3754,[33]1.3757,[34]1.3681,[35]1.3643,[36]1.3595,[37]1.3672,[38]1.3761,[39]1.3676,[40]1.3894,[41]1.3983,[42]1.4012,[43]1.4096,[44]1.4109,[45]1.4046,[46]1.4078,[47]1.4116,[48]1.4128, |
|
|
Final estimate: PPL = 1.4128 +/- 0.00952 |
|
|
|
|
|
llama_perf_context_print: load time = 7919.57 ms |
|
|
llama_perf_context_print: prompt eval time = 855777.23 ms / 98304 tokens ( 8.71 ms per token, 114.87 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 = 857385.44 ms / 98305 tokens |
|
|
llama_perf_context_print: graphs reused = 0 |
|
|
llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | |
|
|
llama_memory_breakdown_print: | - CUDA0 (RTX 3090) | 24115 = 7231 + (12208 = 10300 + 80 + 1828) + 4674 | |
|
|
llama_memory_breakdown_print: | - CUDA1 (RTX 3090) | 24124 = 12270 + (10574 = 10300 + 80 + 194) + 1279 | |
|
|
llama_memory_breakdown_print: | - Host | 69321 = 68955 + 352 + 14 | |
|
|
|
