robbiemu's picture
update for quantization
5dadba4
raw
history blame
9.23 kB
llama-imatrix \
-m ./salamandra-2b_fp16.gguf \
-f ./imatrix-dataset.txt \
-o imatrix.dat \
--ctx-size 8192 \
--rope-freq-base 10000.0 \
--top-p 0.95 \
--temp 0 \
--repeat-penalty 1.2
build: 3906 (7eee341b) with Apple clang version 16.0.0 (clang-1600.0.26.3) for arm64-apple-darwin24.0.0
llama_model_loader: loaded meta data with 29 key-value pairs and 219 tensors from ./salamandra-2b_fp16.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 = 1
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: - type f32: 49 tensors
llama_model_loader: - type f16: 170 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 = F16
llm_load_print_meta: model params = 2.25 B
llm_load_print_meta: model size = 4.20 GiB (16.00 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 = 4298.39 MiB
llm_load_tensors: CPU buffer size = 1000.00 MiB
.......................................................
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
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 = 504.00 MiB
llama_new_context_with_model: CPU compute buffer size = 20.01 MiB
llama_new_context_with_model: graph nodes = 774
llama_new_context_with_model: graph splits = 2
system_info: n_threads = 12 (n_threads_batch = 12) / 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 |
compute_imatrix: tokenizing the input ..
compute_imatrix: tokenization took 340.666 ms
compute_imatrix: computing over 23 chunks with batch_size 2048
compute_imatrix: 9.14 seconds per pass - ETA 3.50 minutes
[1]7.0436,[2]10.2362,[3]13.6287,[4]14.7220,[5]14.4533,[6]12.6333,[7]14.2159,[8]14.9075,[9]14.3021,[10]13.8248,[11]14.9012,[12]14.2073,[13]14.7439,[14]15.3755,[15]15.8260,[16]16.6927,[17]15.8323,[18]15.6479,[19]15.3194,[20]15.1174,[21]14.2193,[22]14.0684,[23]13.9231,
Final estimate: PPL = 13.9231 +/- 0.13493
llama_perf_context_print: load time = 2593.90 ms
llama_perf_context_print: prompt eval time = 178500.98 ms / 188416 tokens ( 0.95 ms per token, 1055.55 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 = 212778.10 ms / 188417 tokens
ggml_metal_free: deallocating