|
|
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) - 20231 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 36 key-value pairs and 398 tensors from /mnt/world8/AI/ToBench/Qwen3-4B-Instruct-2507-unsloth/Magic_Quant/GGUF/Qwen3-4B-Instruct-2507-unsloth-Q5_K.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 = qwen3 |
|
|
llama_model_loader: - kv 1: general.type str = model |
|
|
llama_model_loader: - kv 2: general.name str = Qwen3 4B 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 = 4B |
|
|
llama_model_loader: - kv 7: general.license str = apache-2.0 |
|
|
llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/Qwen3-4B-... |
|
|
llama_model_loader: - kv 9: general.base_model.count u32 = 1 |
|
|
llama_model_loader: - kv 10: general.base_model.0.name str = Qwen3 4B 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/Qwen3-4B-... |
|
|
llama_model_loader: - kv 14: general.tags arr[str,2] = ["unsloth", "text-generation"] |
|
|
llama_model_loader: - kv 15: qwen3.block_count u32 = 36 |
|
|
llama_model_loader: - kv 16: qwen3.context_length u32 = 262144 |
|
|
llama_model_loader: - kv 17: qwen3.embedding_length u32 = 2560 |
|
|
llama_model_loader: - kv 18: qwen3.feed_forward_length u32 = 9728 |
|
|
llama_model_loader: - kv 19: qwen3.attention.head_count u32 = 32 |
|
|
llama_model_loader: - kv 20: qwen3.attention.head_count_kv u32 = 8 |
|
|
llama_model_loader: - kv 21: qwen3.rope.freq_base f32 = 5000000.000000 |
|
|
llama_model_loader: - kv 22: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 |
|
|
llama_model_loader: - kv 23: qwen3.attention.key_length u32 = 128 |
|
|
llama_model_loader: - kv 24: qwen3.attention.value_length u32 = 128 |
|
|
llama_model_loader: - kv 25: tokenizer.ggml.model str = gpt2 |
|
|
llama_model_loader: - kv 26: tokenizer.ggml.pre str = qwen2 |
|
|
llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... |
|
|
llama_model_loader: - kv 28: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... |
|
|
llama_model_loader: - kv 29: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... |
|
|
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 151645 |
|
|
llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 151654 |
|
|
llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false |
|
|
llama_model_loader: - kv 33: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... |
|
|
llama_model_loader: - kv 34: general.quantization_version u32 = 2 |
|
|
llama_model_loader: - kv 35: general.file_type u32 = 17 |
|
|
llama_model_loader: - type f32: 145 tensors |
|
|
llama_model_loader: - type q5_K: 216 tensors |
|
|
llama_model_loader: - type q6_K: 37 tensors |
|
|
print_info: file format = GGUF V3 (latest) |
|
|
print_info: file type = Q5_K - Medium |
|
|
print_info: file size = 2.69 GiB (5.73 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 = qwen3 |
|
|
print_info: vocab_only = 0 |
|
|
print_info: n_ctx_train = 262144 |
|
|
print_info: n_embd = 2560 |
|
|
print_info: n_embd_inp = 2560 |
|
|
print_info: n_layer = 36 |
|
|
print_info: n_head = 32 |
|
|
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 = 4 |
|
|
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 = 9728 |
|
|
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 = -1 |
|
|
print_info: rope type = 2 |
|
|
print_info: rope scaling = linear |
|
|
print_info: freq_base_train = 5000000.0 |
|
|
print_info: freq_scale_train = 1 |
|
|
print_info: n_ctx_orig_yarn = 262144 |
|
|
print_info: rope_finetuned = unknown |
|
|
print_info: model type = 4B |
|
|
print_info: model params = 4.02 B |
|
|
print_info: general.name = Qwen3 4B Instruct 2507 Unsloth |
|
|
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 20/37 layers to GPU |
|
|
load_tensors: CPU_Mapped model buffer size = 1391.26 MiB |
|
|
load_tensors: CUDA0 model buffer size = 672.38 MiB |
|
|
load_tensors: CUDA1 model buffer size = 686.33 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 = 5000000.0 |
|
|
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 = 128.00 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 = 288.00 MiB ( 2048 cells, 36 layers, 1/1 seqs), K (f16): 144.00 MiB, V (f16): 144.00 MiB |
|
|
llama_context: Flash Attention was auto, set to enabled |
|
|
llama_context: CUDA0 compute buffer size = 606.03 MiB |
|
|
llama_context: CUDA1 compute buffer size = 74.01 MiB |
|
|
llama_context: CUDA_Host compute buffer size = 9.01 MiB |
|
|
llama_context: graph nodes = 1267 |
|
|
llama_context: graph splits = 213 (with bs=512), 52 (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 45.478 ms |
|
|
perplexity: calculating perplexity over 16 chunks, n_ctx=2048, batch_size=2048, n_seq=1 |
|
|
perplexity: 1.08 seconds per pass - ETA 0.28 minutes |
|
|
[1]5.6200,[2]6.2013,[3]6.4562,[4]6.6412,[5]6.8836,[6]6.8246,[7]6.7873,[8]6.6877,[9]6.7166,[10]6.6714,[11]6.7073,[12]6.6928,[13]6.7765,[14]6.7818,[15]6.7798,[16]6.7701, |
|
|
Final estimate: PPL = 6.7701 +/- 0.13838 |
|
|
|
|
|
llama_perf_context_print: load time = 592.92 ms |
|
|
llama_perf_context_print: prompt eval time = 14105.61 ms / 32768 tokens ( 0.43 ms per token, 2323.05 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 = 14559.29 ms / 32769 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 = 18774 + (1358 = 672 + 80 + 606) + 3981 | |
|
|
llama_memory_breakdown_print: | - CUDA1 (RTX 3090) | 24124 = 22120 + ( 840 = 686 + 80 + 74) + 1163 | |
|
|
llama_memory_breakdown_print: | - Host | 1528 = 1391 + 128 + 9 | |
|
|
|
