qsbye/runtime-env10 repository overview

# arm64
# docker run -it --rm -v $PWD:/srv qsbye/runtime-env10:v0.1-arm64 /main -m /models/MiniCPM-2B-dpo-q4km-gguf.gguf --prompt "<用户>写藏头诗，藏头是龙年大吉<AI>" --temp 0.3 --top-p 0.8 --repeat-penalty 1.05 -e
docker run -it --rm -v $PWD:/srv qsbye/runtime-env10:v0.1-arm64 /main -m /models --prompt "<用户>写藏头诗，藏头是龙年大吉<AI>" --temp 0.3 --top-p 0.8 --repeat-penalty 1.05 -e

temp 0.3 --top-p 0.8 --repeat-penalty 1.05 -e
Log start
main: build = 2110 (7c777fcd)
main: built with cc (GCC) 9.5.0 for aarch64-linux-gnu
main: seed  = 1707919586
llama_model_loader: loaded meta data with 22 key-value pairs and 362 tensors from /models (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              = minicpm
llama_model_loader: - kv   1:                               general.name str              = MiniCPM
llama_model_loader: - kv   2:                     minicpm.context_length u32              = 2048
llama_model_loader: - kv   3:                   minicpm.embedding_length u32              = 2304
llama_model_loader: - kv   4:                        minicpm.block_count u32              = 40
llama_model_loader: - kv   5:                minicpm.feed_forward_length u32              = 5760
llama_model_loader: - kv   6:               minicpm.rope.dimension_count u32              = 64
llama_model_loader: - kv   7:               minicpm.attention.head_count u32              = 36
llama_model_loader: - kv   8:            minicpm.attention.head_count_kv u32              = 36
llama_model_loader: - kv   9:   minicpm.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                          general.file_type u32              = 15
llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr[str,122753]  = ["<unk>", "<s>", "</s>", "<SEP>", "<C...
llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr[f32,122753]  = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,122753]  = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  18:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  19:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% for message in messages %}{% if me...
llama_model_loader: - kv  21:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q5_0:   20 tensors
llama_model_loader: - type q8_0:   20 tensors
llama_model_loader: - type q4_K:  221 tensors
llama_model_loader: - type q6_K:   20 tensors
llm_load_vocab: mismatch in special tokens definition ( 3528/122753 vs 259/122753 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = minicpm
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 122753
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 2048
llm_load_print_meta: n_embd           = 2304
llm_load_print_meta: n_head           = 36
llm_load_print_meta: n_head_kv        = 36
llm_load_print_meta: n_layer          = 40
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_embd_head_k    = 64
llm_load_print_meta: n_embd_head_v    = 64
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 2304
llm_load_print_meta: n_embd_v_gqa     = 2304
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: n_ff             = 5760
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 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_yarn_orig_ctx  = 2048
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: model type       = 2B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 2.72 B
llm_load_print_meta: model size       = 1.61 GiB (5.07 BPW) 
llm_load_print_meta: general.name     = MiniCPM
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         = 1099 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.14 MiB
llm_load_tensors:        CPU buffer size =  1646.66 MiB
............................................................................................
llama_new_context_with_model: n_ctx      = 512
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:        CPU KV buffer size =   180.00 MiB
llama_new_context_with_model: KV self size  =  180.00 MiB, K (f16):   90.00 MiB, V (f16):   90.00 MiB
llama_new_context_with_model:        CPU input buffer size   =     5.51 MiB
llama_new_context_with_model:        CPU compute buffer size =   268.68 MiB
llama_new_context_with_model: graph splits (measure): 1

system_info: n_threads = 4 / 4 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | 
sampling: 
	repeat_last_n = 64, repeat_penalty = 1.050, frequency_penalty = 0.000, presence_penalty = 0.000
	top_k = 40, tfs_z = 1.000, top_p = 0.800, min_p = 0.050, typical_p = 1.000, temp = 0.300
	mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order: 
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temp 
generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 0


 <用户>写藏头诗，藏头是龙年大吉<AI> 龙飞凤舞庆丰年，
瑞气祥云绕帝宸。
岁稔民安歌乐事，
岁寒松柏见精神。 [end of text]

llama_print_timings:        load time =     771.31 ms
llama_print_timings:      sample time =       8.05 ms /    34 runs   (    0.24 ms per token,  4225.18 tokens per second)
llama_print_timings: prompt eval time =     986.12 ms /    19 tokens (   51.90 ms per token,    19.27 tokens per second)
llama_print_timings:        eval time =    1840.55 ms /    33 runs   (   55.77 ms per token,    17.93 tokens per second)
llama_print_timings:       total time =    2845.07 ms /    52 tokens
Log end