Original repo: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct
Note: Make sure you have enough CPUs resources, otherwise it will load failed.
ec2-user@ip-10-110-145-52:~/workspace/llama.cpp$ ./llama-cli -m ../Phi-3-medium-128k-instruct/phi3-medium-128k-instruct-Q4_K_M-v2.gguf -n 128 --repeat_penalty 1.0 --co
lor -i -r "User:" -f prompts/chat-with-bob.txt
Log start
main: build = 3233 (a8d49d86)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1719626314
llama_model_loader: loaded meta data with 27 key-value pairs and 245 tensors from ../Phi-3-medium-128k-instruct/phi3-medium-128k-instruct-Q4_K_M-v2.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 = phi3
llama_model_loader: - kv 1: general.name str = Phi3
llama_model_loader: - kv 2: phi3.context_length u32 = 131072
llama_model_loader: - kv 3: phi3.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 4: phi3.embedding_length u32 = 5120
llama_model_loader: - kv 5: phi3.feed_forward_length u32 = 17920
llama_model_loader: - kv 6: phi3.block_count u32 = 40
llama_model_loader: - kv 7: phi3.attention.head_count u32 = 40
llama_model_loader: - kv 8: phi3.attention.head_count_kv u32 = 10
llama_model_loader: - kv 9: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: phi3.rope.dimension_count u32 = 128
llama_model_loader: - kv 11: phi3.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 12: general.file_type u32 = 15
llama_model_loader: - kv 13: phi3.rope.scaling.attn_factor f32 = 1.190238
llama_model_loader: - kv 14: tokenizer.ggml.model str = llama
llama_model_loader: - kv 15: tokenizer.ggml.pre str = default
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,32064] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,32064] = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 32000
llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 32000
llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 24: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 25: tokenizer.chat_template str = {% for message in messages %}{% if (m...
llama_model_loader: - kv 26: general.quantization_version u32 = 2
llama_model_loader: - type f32: 83 tensors
llama_model_loader: - type q4_K: 101 tensors
llama_model_loader: - type q5_K: 40 tensors
llama_model_loader: - type q6_K: 21 tensors
llm_load_vocab: special tokens cache size = 323
llm_load_vocab: token to piece cache size = 0.1687 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = phi3
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32064
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 5120
llm_load_print_meta: n_head = 40
llm_load_print_meta: n_head_kv = 10
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1280
llm_load_print_meta: n_embd_v_gqa = 1280
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 = 17920
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 = 2
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 = 4096
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: model type = 14B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 13.96 B
llm_load_print_meta: model size = 7.98 GiB (4.91 BPW)
llm_load_print_meta: general.name = Phi3
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 32000 '<|endoftext|>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 32000 '<|endoftext|>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_print_meta: EOT token = 32007 '<|end|>'
llm_load_print_meta: max token length = 48
llm_load_tensors: ggml ctx size = 0.13 MiB
llm_load_tensors: CPU buffer size = 8169.25 MiB