Views
No views yet
1
2system_info: n_threads = 4 / 8 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
3main: interactive mode on.
4Reverse prompt: 'User:'
5sampling:
6 repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
7 top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
8 mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
9sampling order:
10CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
11generate: n_ctx = 1024, n_batch = 2048, n_predict = 256, n_keep = 0
12
13
14== Running in interactive mode. ==
15 - Press Ctrl+C to interject at any time.
16 - Press Return to return control to the AI.
17 - To return control without starting a new line, end your input with '/'.
18 - If you want to submit another line, end your input with '\'.
19
20Transcript of a dialog, where the User interacts with an Assistant named Bob. Bob is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.
21
22User: Hello, Bob.
23Bob: Hello. How may I help you today?
24User: Please tell me the largest city in Europe.
25Bob: Sure. The largest city in Europe is Moscow, the capital of Russia.
26User:What is the largest city in Australia?
27
28Bob: The largest city in Australia is Melbourne, the capital of Victoria.
29
30User:What is the largest city in US
31
32Bob: The largest city in US is Los Angeles, the capital of California.
33
34User:thanks
35
36Bob:Thanks for calling.
37
38Bob is not a robot, and may be a human being who is not a robot. Bob is an Assistant that is helpful, kind, honest, good at writing and never fails to answer the User's requests.
39
40User:
41
42llama_print_timings: load time = 227.51 ms
43llama_print_timings: sample time = 3.31 ms / 97 runs ( 0.03 ms per token, 29269.76 tokens per second)
44llama_print_timings: prompt eval time = 29632.23 ms / 116 tokens ( 255.45 ms per token, 3.91 tokens per second)
45llama_print_timings: eval time = 4239.84 ms / 94 runs ( 45.10 ms per token, 22.17 tokens per second)
46llama_print_timings: total time = 76118.37 ms / 210 tokens