Donato Capitella
166 lines
11 KiB
Plaintext
166 lines
11 KiB
Plaintext
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
|
|
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
|
|
ggml_cuda_init: found 1 ROCm devices:
|
|
Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32
|
|
build: 6040 (66625a59) with cc (GCC) 15.1.1 20250719 (Red Hat 15.1.1-5) for x86_64-redhat-linux
|
|
main: llama backend init
|
|
main: load the model and apply lora adapter, if any
|
|
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) - 124523 MiB free
|
|
llama_model_loader: loaded meta data with 40 key-value pairs and 626 tensors from /home/kyuz0/models/gemma-3-12b-it-UD-Q8_K_XL/gemma-3-12b-it-UD-Q8_K_XL.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 = gemma3
|
|
llama_model_loader: - kv 1: general.type str = model
|
|
llama_model_loader: - kv 2: general.name str = Gemma-3-12B-It
|
|
llama_model_loader: - kv 3: general.finetune str = it
|
|
llama_model_loader: - kv 4: general.basename str = Gemma-3-12B-It
|
|
llama_model_loader: - kv 5: general.quantized_by str = Unsloth
|
|
llama_model_loader: - kv 6: general.size_label str = 12B
|
|
llama_model_loader: - kv 7: general.repo_url str = https://huggingface.co/unsloth
|
|
llama_model_loader: - kv 8: gemma3.context_length u32 = 131072
|
|
llama_model_loader: - kv 9: gemma3.embedding_length u32 = 3840
|
|
llama_model_loader: - kv 10: gemma3.block_count u32 = 48
|
|
llama_model_loader: - kv 11: gemma3.feed_forward_length u32 = 15360
|
|
llama_model_loader: - kv 12: gemma3.attention.head_count u32 = 16
|
|
llama_model_loader: - kv 13: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
|
|
llama_model_loader: - kv 14: gemma3.attention.key_length u32 = 256
|
|
llama_model_loader: - kv 15: gemma3.attention.value_length u32 = 256
|
|
llama_model_loader: - kv 16: gemma3.rope.freq_base f32 = 1000000.000000
|
|
llama_model_loader: - kv 17: gemma3.attention.sliding_window u32 = 1024
|
|
llama_model_loader: - kv 18: gemma3.attention.head_count_kv u32 = 8
|
|
llama_model_loader: - kv 19: gemma3.rope.scaling.type str = linear
|
|
llama_model_loader: - kv 20: gemma3.rope.scaling.factor f32 = 8.000000
|
|
llama_model_loader: - kv 21: tokenizer.ggml.model str = llama
|
|
llama_model_loader: - kv 22: tokenizer.ggml.pre str = default
|
|
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,262208] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
|
|
llama_model_loader: - kv 24: tokenizer.ggml.scores arr[f32,262208] = [-1000.000000, -1000.000000, -1000.00...
|
|
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,262208] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
|
|
llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 2
|
|
llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 106
|
|
llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 3
|
|
llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 0
|
|
llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true
|
|
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = false
|
|
llama_model_loader: - kv 32: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
|
|
llama_model_loader: - kv 33: tokenizer.ggml.add_space_prefix bool = false
|
|
llama_model_loader: - kv 34: general.quantization_version u32 = 2
|
|
llama_model_loader: - kv 35: general.file_type u32 = 7
|
|
llama_model_loader: - kv 36: quantize.imatrix.file str = gemma-3-12b-it-GGUF/imatrix_unsloth.dat
|
|
llama_model_loader: - kv 37: quantize.imatrix.dataset str = unsloth_calibration_gemma-3-12b-it.txt
|
|
llama_model_loader: - kv 38: quantize.imatrix.entries_count i32 = 336
|
|
llama_model_loader: - kv 39: quantize.imatrix.chunks_count i32 = 663
|
|
llama_model_loader: - type f32: 289 tensors
|
|
llama_model_loader: - type q8_0: 311 tensors
|
|
llama_model_loader: - type bf16: 26 tensors
|
|
print_info: file format = GGUF V3 (latest)
|
|
print_info: file type = Q8_0
|
|
print_info: file size = 13.40 GiB (9.78 BPW)
|
|
load: special tokens cache size = 6415
|
|
load: token to piece cache size = 1.9446 MB
|
|
print_info: arch = gemma3
|
|
print_info: vocab_only = 0
|
|
print_info: n_ctx_train = 131072
|
|
print_info: n_embd = 3840
|
|
print_info: n_layer = 48
|
|
print_info: n_head = 16
|
|
print_info: n_head_kv = 8
|
|
print_info: n_rot = 256
|
|
print_info: n_swa = 1024
|
|
print_info: is_swa_any = 1
|
|
print_info: n_embd_head_k = 256
|
|
print_info: n_embd_head_v = 256
|
|
print_info: n_gqa = 2
|
|
print_info: n_embd_k_gqa = 2048
|
|
print_info: n_embd_v_gqa = 2048
|
|
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 = 6.2e-02
|
|
print_info: n_ff = 15360
|
|
print_info: n_expert = 0
|
|
print_info: n_expert_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 = 1000000.0
|
|
print_info: freq_scale_train = 0.125
|
|
print_info: n_ctx_orig_yarn = 131072
|
|
print_info: rope_finetuned = unknown
|
|
print_info: model type = 12B
|
|
print_info: model params = 11.77 B
|
|
print_info: general.name = Gemma-3-12B-It
|
|
print_info: vocab type = SPM
|
|
print_info: n_vocab = 262208
|
|
print_info: n_merges = 0
|
|
print_info: BOS token = 2 '<bos>'
|
|
print_info: EOS token = 106 '<end_of_turn>'
|
|
print_info: EOT token = 106 '<end_of_turn>'
|
|
print_info: UNK token = 3 '<unk>'
|
|
print_info: PAD token = 0 '<pad>'
|
|
print_info: LF token = 248 '<0x0A>'
|
|
print_info: EOG token = 106 '<end_of_turn>'
|
|
print_info: max token length = 48
|
|
load_tensors: loading model tensors, this can take a while... (mmap = false)
|
|
load_tensors: offloading 48 repeating layers to GPU
|
|
load_tensors: offloading output layer to GPU
|
|
load_tensors: offloaded 49/49 layers to GPU
|
|
load_tensors: ROCm0 model buffer size = 13721.20 MiB
|
|
load_tensors: ROCm_Host model buffer size = 1920.47 MiB
|
|
.............................................................................
|
|
llama_context: constructing llama_context
|
|
llama_context: non-unified KV cache requires ggml_set_rows() - forcing unified KV cache
|
|
llama_context: n_seq_max = 1
|
|
llama_context: n_ctx = 4096
|
|
llama_context: n_ctx_per_seq = 4096
|
|
llama_context: n_batch = 2048
|
|
llama_context: n_ubatch = 512
|
|
llama_context: causal_attn = 1
|
|
llama_context: flash_attn = 1
|
|
llama_context: kv_unified = true
|
|
llama_context: freq_base = 1000000.0
|
|
llama_context: freq_scale = 0.125
|
|
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
|
|
llama_context: ROCm_Host output buffer size = 1.00 MiB
|
|
llama_kv_cache_unified_iswa: creating non-SWA KV cache, size = 4096 cells
|
|
llama_kv_cache_unified: ROCm0 KV buffer size = 256.00 MiB
|
|
llama_kv_cache_unified: size = 256.00 MiB ( 4096 cells, 8 layers, 1/ 1 seqs), K (f16): 128.00 MiB, V (f16): 128.00 MiB
|
|
llama_kv_cache_unified: LLAMA_SET_ROWS=0, using old ggml_cpy() method for backwards compatibility
|
|
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 1536 cells
|
|
llama_kv_cache_unified: ROCm0 KV buffer size = 480.00 MiB
|
|
llama_kv_cache_unified: size = 480.00 MiB ( 1536 cells, 40 layers, 1/ 1 seqs), K (f16): 240.00 MiB, V (f16): 240.00 MiB
|
|
llama_kv_cache_unified: LLAMA_SET_ROWS=0, using old ggml_cpy() method for backwards compatibility
|
|
llama_context: ROCm0 compute buffer size = 519.62 MiB
|
|
llama_context: ROCm_Host compute buffer size = 11.01 MiB
|
|
llama_context: graph nodes = 2025
|
|
llama_context: graph splits = 1
|
|
common_init_from_params: KV cache shifting is not supported for this context, disabling KV cache shifting
|
|
common_init_from_params: added <end_of_turn> logit bias = -inf
|
|
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
|
|
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
|
|
main: llama threadpool init, n_threads = 16
|
|
|
|
system_info: n_threads = 16 (n_threads_batch = 16) / 32 | ROCm : NO_VMM = 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 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
|
|
|
|
sampler seed: 854716185
|
|
sampler params:
|
|
repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
|
|
dry_multiplier = 0.000, dry_base = 1.750, dry_allowed_length = 2, dry_penalty_last_n = 4096
|
|
top_k = 40, top_p = 0.950, min_p = 0.050, xtc_probability = 0.000, xtc_threshold = 0.100, typical_p = 1.000, top_n_sigma = -1.000, temp = 0.800
|
|
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
|
|
sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
|
|
generate: n_ctx = 4096, n_batch = 2048, n_predict = 1, n_keep = 1
|
|
|
|
HelloWhat
|
|
|
|
llama_perf_sampler_print: sampling time = 0.14 ms / 3 runs ( 0.05 ms per token, 21428.57 tokens per second)
|
|
llama_perf_context_print: load time = 2695.72 ms
|
|
llama_perf_context_print: prompt eval time = 75.18 ms / 2 tokens ( 37.59 ms per token, 26.60 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 = 82.57 ms / 3 tokens
|
|
llama_perf_context_print: graphs reused = 0
|
|
Elapsed #3: 3.208919123s
|
|
Run #3 status: 0
|
|
→ Avg over 3 runs: 3.434s
|