Bug:

[tonychan09]

Contact Details

tony.kw.chan@live.com

What happened?

OS: Windows
Llama file: Tried using 0.6, 0.7 and 0.8
Model: https://huggingface.co/Mozilla/Phi-3-medium-128k-instruct-llamafile

Getting the following error:
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'phi3'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'Phi-3-medium-128k-instruct.BF16.gguf'

Is there a later version of llamafile that supports the Phi3 architecture?

Thanks

Version

llamafile-0.8

What operating system are you seeing the problem on?

Windows

Relevant log output

note: if you have an AMD or NVIDIA GPU then you need to pass -ngl 9999 to enable GPU offloading
{"build":1500,"commit":"a30b324","function":"server_cli","level":"INFO","line":2859,"msg":"build info","tid":"9434528","timestamp":1721860157}
{"function":"server_cli","level":"INFO","line":2862,"msg":"system info","n_threads":6,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | ","tid":"9434528","timestamp":1721860157,"total_threads":12}
llama_model_loader: loaded meta data with 27 key-value pairs and 245 tensors from Phi-3-medium-128k-instruct.BF16.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              = 32
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 bf16:  162 tensors
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'phi3'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'Phi-3-medium-128k-instruct.BF16.gguf'
{"function":"load_model","level":"ERR","line":447,"model":"Phi-3-medium-128k-instruct.BF16.gguf","msg":"unable to load model","tid":"9434528","timestamp":1721860157}

[jart]

Yes. Download the latest llamafile release as follows:

curl -o llamafile.exe https://github.com/Mozilla-Ocho/llamafile/releases/download/0.8.11/llamafile-0.8.11

You can then say on windows:

llamafile -m Phi-3-medium-128k-instruct.Q5_0.llamafile

Using the llamafiles you downloaded off the hugging face page.