Update README.md

README.md

@@ -23,6 +23,167 @@ library_name: transformers
 
 **THIS IS A MIRROR OF https://ai.azure.com/explore/models/Phi-4/ ALONG WITH A CONVERTED TOKENIZER FOR llama.cpp**
 
+
+... OK tokenizer seems a bit off
+
+OK, tokenizer seems a bit off 😂
+(llama.cpp) root at nas in /mnt/llm/models llama-cli -m phi-4.etf16-Q6_K.gguf -p "Tell me a joke." -n 256 -t 8 -c 2048 --temp 0.8 -ngl 99
+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: 1153 (d583cd03) with cc (GCC) 14.2.1 20240912 (Red Hat 14.2.1-3) for x86_64-redhat-linux
+main: llama backend init
+main: load the model and apply lora adapter, if any
+llama_load_model_from_file: using device CUDA0 (NVIDIA GeForce RTX 3090) - 24111 MiB free
+llama_load_model_from_file: using device CUDA1 (NVIDIA GeForce RTX 3090) - 24111 MiB free
+llama_model_loader: loaded meta data with 29 key-value pairs and 243 tensors from phi-4.etf16-Q6_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              = phi3
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Phi 4
+llama_model_loader: - kv   3:                            general.version str              = 4
+llama_model_loader: - kv   4:                       general.organization str              = Microsoft
+llama_model_loader: - kv   5:                           general.basename str              = phi
+llama_model_loader: - kv   6:                         general.size_label str              = 15B
+llama_model_loader: - kv   7:                        phi3.context_length u32              = 16384
+llama_model_loader: - kv   8:  phi3.rope.scaling.original_context_length u32              = 16384
+llama_model_loader: - kv   9:                      phi3.embedding_length u32              = 5120
+llama_model_loader: - kv  10:                   phi3.feed_forward_length u32              = 17920
+llama_model_loader: - kv  11:                           phi3.block_count u32              = 40
+llama_model_loader: - kv  12:                  phi3.attention.head_count u32              = 40
+llama_model_loader: - kv  13:               phi3.attention.head_count_kv u32              = 10
+llama_model_loader: - kv  14:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  15:                  phi3.rope.dimension_count u32              = 128
+llama_model_loader: - kv  16:                        phi3.rope.freq_base f32              = 250000.000000
+llama_model_loader: - kv  17:                          general.file_type u32              = 18
+llama_model_loader: - kv  18:              phi3.attention.sliding_window u32              = 100352
+llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,100352]  = ["<unk>", "▁Ġ", "er", "in", "on", ...
+llama_model_loader: - kv  22:                      tokenizer.ggml.scores arr[f32,100352]  = [0.000000, -0.000000, -1.000000, -2.0...
+llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,100352]  = [2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 100257
+llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 100257
+llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 100257
+llama_model_loader: - kv  27:                    tokenizer.chat_template str              = {% for message in messages %}{% if (m...
+llama_model_loader: - kv  28:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   81 tensors
+llama_model_loader: - type  f16:    1 tensors
+llama_model_loader: - type q6_K:  161 tensors
+llm_load_vocab: SPM vocabulary, but newline token not found: unordered_map::at! Using special_pad_id instead.llm_load_vocab: special tokens cache size = 97
+llm_load_vocab: token to piece cache size = 0.7072 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          = 100352
+llm_load_print_meta: n_merges         = 0
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 16384
+llm_load_print_meta: n_embd           = 5120
+llm_load_print_meta: n_layer          = 40
+llm_load_print_meta: n_head           = 40
+llm_load_print_meta: n_head_kv        = 10
+llm_load_print_meta: n_rot            = 128
+llm_load_print_meta: n_swa            = 100352
+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  = 250000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 16384
+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       = 14B
+llm_load_print_meta: model ftype      = Q6_K
+llm_load_print_meta: model params     = 14.66 B
+llm_load_print_meta: model size       = 11.77 GiB (6.89 BPW)
+llm_load_print_meta: general.name     = Phi 4
+llm_load_print_meta: BOS token        = 100257 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 100257 '<|endoftext|>'
+llm_load_print_meta: EOT token        = 100265 '<|im_end|>'
+llm_load_print_meta: UNK token        = 0 '<unk>'
+llm_load_print_meta: PAD token        = 100257 '<|endoftext|>'
+llm_load_print_meta: FIM PRE token    = 100258 '<|fim_prefix|>'
+llm_load_print_meta: FIM SUF token    = 100260 '<|fim_suffix|>'
+llm_load_print_meta: FIM MID token    = 100259 '<|fim_middle|>'
+llm_load_print_meta: EOG token        = 100257 '<|endoftext|>'
+llm_load_print_meta: EOG token        = 100265 '<|im_end|>'
+llm_load_print_meta: max token length = 33
+llm_load_tensors: offloading 40 repeating layers to GPU
+llm_load_tensors: offloading output layer to GPU
+llm_load_tensors: offloaded 41/41 layers to GPU
+llm_load_tensors:   CPU_Mapped model buffer size =   980.00 MiB
+llm_load_tensors:        CUDA0 model buffer size =  5599.45 MiB
+llm_load_tensors:        CUDA1 model buffer size =  5468.14 MiB
+...................................................................................
+llama_new_context_with_model: n_seq_max     = 1
+llama_new_context_with_model: n_ctx         = 2048
+llama_new_context_with_model: n_ctx_per_seq = 2048
+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     = 250000.0
+llama_new_context_with_model: freq_scale    = 1
+llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (16384) -- the full capacity of the model will not be utilized
+llama_kv_cache_init:      CUDA0 KV buffer size =   210.00 MiB
+llama_kv_cache_init:      CUDA1 KV buffer size =   190.00 MiB
+llama_new_context_with_model: KV self size  =  400.00 MiB, K (f16):  200.00 MiB, V (f16):  200.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.38 MiB
+llama_new_context_with_model: pipeline parallelism enabled (n_copies=6)
+llama_new_context_with_model:      CUDA0 compute buffer size =   289.01 MiB
+llama_new_context_with_model:      CUDA1 compute buffer size =   310.02 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    34.04 MiB
+llama_new_context_with_model: graph nodes  = 1606
+llama_new_context_with_model: graph splits = 3
+common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
+main: llama threadpool init, n_threads = 8
+
+system_info: n_threads = 8 (n_threads_batch = 8) / 24 | CUDA : ARCHS = 860 | F16 = 1 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 512 | FA_ALL_QUANTS = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 |
+
+sampler seed: 96750315
+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 = -1
+	top_k = 40, top_p = 0.950, min_p = 0.050, xtc_probability = 0.000, xtc_threshold = 0.100, typical_p = 1.000, temp = 0.800
+	mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
+sampler chain: logits -> logit-bias -> penalties -> dry -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist
+generate: n_ctx = 2048, n_batch = 2048, n_predict = 256, n_keep = 1
+
+ Tell me a joke.ordord Ġteaspoon ĠI Ġteaspoon g Ġteaspoon ĠV Ġteaspoon g Ġteaspoonart Ġteaspoon Ġk Ġteaspoon Aord Ġteaspoonill Ġteaspoon g Ġteaspoon i Ġteaspoonher Ġteaspoon g Ġv Ġtriplet Ġteaspoonart Ġteaspoon Ġk Ġteaspoon ĠIord Ġteaspoon i Ġteaspoon g Ġteaspoon ĠV Ġteaspoonher Ġteaspoon Ġk Ġteaspoonra Ġteaspoon , Ġteaspoon Ġk Ġteaspoon1⁄4ord Ġteaspoon Ġun Ġteaspoon Ġk ĠteaspoonRE Ġteaspoonher Ġteaspoon g Ġteaspoon , Ġteaspoon Ġkord Ġteaspoon1⁄4 Ġteaspoon A Ġteaspoon , Ġteaspoon Ġk Ġteaspoon Aord Ġteaspoon i Ġteaspoon g Ġteaspoonill Ġteaspoonell Ġteaspoon g Ġteaspoon ĠVord Ġteaspoon1⁄4 Ġteaspoonill Ġv Ġtriplet Ġteaspoon ĠD Ġteaspoon1⁄4 Ġteaspoon); Ġteaspoon1⁄4 Ġteaspoon Aord Ġteaspoonell Ġteaspoon1⁄4 Ġteaspoonher Ġteaspoon1⁄4 Ġteaspoonell Ġteaspoon ĠV Ġteaspoon Ġk Ġteaspoon); Ġv Ġtriplet Ġteaspoon ĠIord Ġteaspoonell Ġteaspoon1⁄4ord Ġteaspoon1⁄4 Ġteaspoon A Ġteaspoon , Ġteaspoon g Ġteaspoonart Ġteaspoon Ġk Ġteaspoon Aord Ġteaspoon); Ġv Ġtriplet Ġteaspoonill Ġteaspoon g ĠteaspoonRE Ġteaspoon g Ġteaspoonart Ġteaspoon Aord Ġteaspoon i Ġteaspoon g Ġteaspoonher Ġteaspoon A Ġteaspoon1⁄4 Ġteaspoonher Ġteaspoon , Ġv Ġtriplet Ġteaspoon ĠIord Ġteaspoon A Ġteaspoon1⁄4 Ġteaspoon Ġk Ġteaspoonell Ġteaspoon g Ġteaspoon); Ġteaspoonest Ġteaspoon Ġk Ġteaspoon Ġg Ġteaspoon Ġk Ġteaspoonct Ġteaspoon1⁄4 Ġteaspoon ĠD Ġteaspoon Ġk Ġv Ġtripletord ĠteaspoonRE Ġteaspoon Ġk Ġteaspoon ĠD Ġteaspoonop Ġteaspoonher Ġteaspoon g Ġteaspoonart Ġteaspoon Ġk Ġteaspoon ĠIar [end of text]
+
+
+llama_perf_sampler_print:    sampling time =       6.05 ms /   246 runs   (    0.02 ms per token, 40634.29 tokens per second)
+llama_perf_context_print:        load time =    1693.08 ms
+llama_perf_context_print: prompt eval time =      26.42 ms /     7 tokens (    3.77 ms per token,   264.96 tokens per second)
+llama_perf_context_print:        eval time =    3993.62 ms /   238 runs   (   16.78 ms per token,    59.60 tokens per second)
+llama_perf_context_print:       total time =    4034.65 ms /   245 tokens
+
+
+----
+
+MS model card follows
+
+
 # Phi-4 Model Card 
 
 ## Model Summary