|
|
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) - 20285 MiB free |
|
|
llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) (0000:03:00.0) - 23582 MiB free |
|
|
llama_model_loader: loaded meta data with 39 key-value pairs and 579 tensors from /mnt/world8/AI/Models/Qwen3-30B-A3B-Instruct-2507-unsloth/Magic_Quant/GGUF/Qwen3-30B-A3B-Instruct-2507-unsloth-IQ4_NL.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 = qwen3moe |
|
|
llama_model_loader: - kv 1: general.type str = model |
|
|
llama_model_loader: - kv 2: general.name str = Qwen3 30B A3B Instruct 2507 Unsloth |
|
|
llama_model_loader: - kv 3: general.version str = 2507 |
|
|
llama_model_loader: - kv 4: general.finetune str = Instruct-unsloth |
|
|
llama_model_loader: - kv 5: general.basename str = Qwen3 |
|
|
llama_model_loader: - kv 6: general.size_label str = 30B-A3B |
|
|
llama_model_loader: - kv 7: general.license str = apache-2.0 |
|
|
llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/Qwen3-30B... |
|
|
llama_model_loader: - kv 9: general.base_model.count u32 = 1 |
|
|
llama_model_loader: - kv 10: general.base_model.0.name str = Qwen3 30B A3B Instruct 2507 |
|
|
llama_model_loader: - kv 11: general.base_model.0.version str = 2507 |
|
|
llama_model_loader: - kv 12: general.base_model.0.organization str = Qwen |
|
|
llama_model_loader: - kv 13: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-30B... |
|
|
llama_model_loader: - kv 14: general.tags arr[str,2] = ["unsloth", "text-generation"] |
|
|
llama_model_loader: - kv 15: qwen3moe.block_count u32 = 48 |
|
|
llama_model_loader: - kv 16: qwen3moe.context_length u32 = 262144 |
|
|
llama_model_loader: - kv 17: qwen3moe.embedding_length u32 = 2048 |
|
|
llama_model_loader: - kv 18: qwen3moe.feed_forward_length u32 = 6144 |
|
|
llama_model_loader: - kv 19: qwen3moe.attention.head_count u32 = 32 |
|
|
llama_model_loader: - kv 20: qwen3moe.attention.head_count_kv u32 = 4 |
|
|
llama_model_loader: - kv 21: qwen3moe.rope.freq_base f32 = 10000000.000000 |
|
|
llama_model_loader: - kv 22: qwen3moe.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
|
llama_model_loader: - kv 23: qwen3moe.expert_used_count u32 = 8 |
|
|
llama_model_loader: - kv 24: qwen3moe.attention.key_length u32 = 128 |
|
|
llama_model_loader: - kv 25: qwen3moe.attention.value_length u32 = 128 |
|
|
llama_model_loader: - kv 26: qwen3moe.expert_count u32 = 128 |
|
|
llama_model_loader: - kv 27: qwen3moe.expert_feed_forward_length u32 = 768 |
|
|
llama_model_loader: - kv 28: tokenizer.ggml.model str = gpt2 |
|
|
llama_model_loader: - kv 29: tokenizer.ggml.pre str = qwen2 |
|
|
llama_model_loader: - kv 30: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... |
|
|
llama_model_loader: - kv 31: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
|
llama_model_loader: - kv 32: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... |
|
|
llama_model_loader: - kv 33: tokenizer.ggml.eos_token_id u32 = 151645 |
|
|
llama_model_loader: - kv 34: tokenizer.ggml.padding_token_id u32 = 151654 |
|
|
llama_model_loader: - kv 35: tokenizer.ggml.add_bos_token bool = false |
|
|
llama_model_loader: - kv 36: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... |
|
|
llama_model_loader: - kv 37: general.quantization_version u32 = 2 |
|
|
llama_model_loader: - kv 38: general.file_type u32 = 25 |
|
|
llama_model_loader: - type f32: 241 tensors |
|
|
llama_model_loader: - type q5_K: 54 tensors |
|
|
llama_model_loader: - type q6_K: 1 tensors |
|
|
llama_model_loader: - type iq4_nl: 283 tensors |
|
|
print_info: file format = GGUF V3 (latest) |
|
|
print_info: file type = IQ4_NL - 4.5 bpw |
|
|
print_info: file size = 16.26 GiB (4.57 BPW) |
|
|
load: printing all EOG tokens: |
|
|
load: - 151643 ('<|endoftext|>') |
|
|
load: - 151645 ('<|im_end|>') |
|
|
load: - 151662 ('<|fim_pad|>') |
|
|
load: - 151663 ('<|repo_name|>') |
|
|
load: - 151664 ('<|file_sep|>') |
|
|
load: special tokens cache size = 26 |
|
|
load: token to piece cache size = 0.9311 MB |
|
|
print_info: arch = qwen3moe |
|
|
print_info: vocab_only = 0 |
|
|
print_info: n_ctx_train = 262144 |
|
|
print_info: n_embd = 2048 |
|
|
print_info: n_embd_inp = 2048 |
|
|
print_info: n_layer = 48 |
|
|
print_info: n_head = 32 |
|
|
print_info: n_head_kv = 4 |
|
|
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 = 8 |
|
|
print_info: n_embd_k_gqa = 512 |
|
|
print_info: n_embd_v_gqa = 512 |
|
|
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 = 6144 |
|
|
print_info: n_expert = 128 |
|
|
print_info: n_expert_used = 8 |
|
|
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 = 262144 |
|
|
print_info: rope_finetuned = unknown |
|
|
print_info: model type = 30B.A3B |
|
|
print_info: model params = 30.53 B |
|
|
print_info: general.name = Qwen3 30B A3B Instruct 2507 Unsloth |
|
|
print_info: n_ff_exp = 768 |
|
|
print_info: vocab type = BPE |
|
|
print_info: n_vocab = 151936 |
|
|
print_info: n_merges = 151387 |
|
|
print_info: BOS token = 11 ',' |
|
|
print_info: EOS token = 151645 '<|im_end|>' |
|
|
print_info: EOT token = 151645 '<|im_end|>' |
|
|
print_info: PAD token = 151654 '<|vision_pad|>' |
|
|
print_info: LF token = 198 'Ċ' |
|
|
print_info: FIM PRE token = 151659 '<|fim_prefix|>' |
|
|
print_info: FIM SUF token = 151661 '<|fim_suffix|>' |
|
|
print_info: FIM MID token = 151660 '<|fim_middle|>' |
|
|
print_info: FIM PAD token = 151662 '<|fim_pad|>' |
|
|
print_info: FIM REP token = 151663 '<|repo_name|>' |
|
|
print_info: FIM SEP token = 151664 '<|file_sep|>' |
|
|
print_info: EOG token = 151643 '<|endoftext|>' |
|
|
print_info: EOG token = 151645 '<|im_end|>' |
|
|
print_info: EOG token = 151662 '<|fim_pad|>' |
|
|
print_info: EOG token = 151663 '<|repo_name|>' |
|
|
print_info: EOG token = 151664 '<|file_sep|>' |
|
|
print_info: max token length = 256 |
|
|
load_tensors: loading model tensors, this can take a while... (mmap = true) |
|
|
load_tensors: offloading 20 repeating layers to GPU |
|
|
load_tensors: offloaded 20/49 layers to GPU |
|
|
load_tensors: CPU_Mapped model buffer size = 9941.82 MiB |
|
|
load_tensors: CUDA0 model buffer size = 3352.67 MiB |
|
|
load_tensors: CUDA1 model buffer size = 3352.67 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 (262144) -- the full capacity of the model will not be utilized |
|
|
llama_context: CPU output buffer size = 0.58 MiB |
|
|
llama_kv_cache: CPU KV buffer size = 112.00 MiB |
|
|
llama_kv_cache: CUDA0 KV buffer size = 40.00 MiB |
|
|
llama_kv_cache: CUDA1 KV buffer size = 40.00 MiB |
|
|
llama_kv_cache: size = 192.00 MiB ( 2048 cells, 48 layers, 1/1 seqs), K (f16): 96.00 MiB, V (f16): 96.00 MiB |
|
|
llama_context: Flash Attention was auto, set to enabled |
|
|
llama_context: CUDA0 compute buffer size = 544.18 MiB |
|
|
llama_context: CUDA1 compute buffer size = 82.01 MiB |
|
|
llama_context: CUDA_Host compute buffer size = 8.01 MiB |
|
|
llama_context: graph nodes = 3031 |
|
|
llama_context: graph splits = 397 (with bs=512), 88 (with bs=1) |
|
|
common_init_from_params: added <|endoftext|> logit bias = -inf |
|
|
common_init_from_params: added <|im_end|> logit bias = -inf |
|
|
common_init_from_params: added <|fim_pad|> logit bias = -inf |
|
|
common_init_from_params: added <|repo_name|> logit bias = -inf |
|
|
common_init_from_params: added <|file_sep|> 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 117.169 ms |
|
|
perplexity: calculating perplexity over 44 chunks, n_ctx=2048, batch_size=2048, n_seq=1 |
|
|
perplexity: 3.52 seconds per pass - ETA 2.57 minutes |
|
|
[1]1.6042,[2]1.4795,[3]1.2984,[4]1.2576,[5]1.3428,[6]1.4086,[7]1.4068,[8]1.4038,[9]1.3642,[10]1.3422,[11]1.3260,[12]1.3282,[13]1.3134,[14]1.3048,[15]1.3015,[16]1.2896,[17]1.2828,[18]1.2826,[19]1.2755,[20]1.2652,[21]1.2618,[22]1.2617,[23]1.2783,[24]1.2715,[25]1.2707,[26]1.2624,[27]1.2569,[28]1.2556,[29]1.2685,[30]1.2696,[31]1.2631,[32]1.2583,[33]1.2589,[34]1.2584,[35]1.2571,[36]1.2785,[37]1.2884,[38]1.2932,[39]1.2996,[40]1.3004,[41]1.2976,[42]1.3107,[43]1.3104,[44]1.3111, |
|
|
Final estimate: PPL = 1.3111 +/- 0.00733 |
|
|
|
|
|
llama_perf_context_print: load time = 2476.04 ms |
|
|
llama_perf_context_print: prompt eval time = 127598.35 ms / 90112 tokens ( 1.42 ms per token, 706.22 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 = 128837.59 ms / 90113 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 = 16274 + ( 3936 = 3352 + 40 + 544) + 3903 | |
|
|
llama_memory_breakdown_print: | - CUDA1 (RTX 3090) | 24124 = 19998 + ( 3474 = 3352 + 40 + 82) + 651 | |
|
|
llama_memory_breakdown_print: | - Host | 10061 = 9941 + 112 + 8 | |
|
|
|
