LLM test on Discrete GPU 6800M vs Integrated

##################### With Discrete GPU 6800M - gfx1031c
D:\Apps\llama\llama-master-a113689-bin-win-clblast-x64\main.exe -m D:\Apps\llama\nous-hermes-llama2-13b.ggmlv3.q4_1.bin -ngl 50  -i --threads 8 --interactive-first -r "### Human:" --temp 0.7 -c 2048 --top_k 40 --top_p 0.1 --repeat_last_n 0 --repeat_penalty 1.1764705882352942 --instruct
main: build = 929 (a113689)
main: seed  = 1690903767
ggml_opencl: selecting platform: 'AMD Accelerated Parallel Processing'
ggml_opencl: selecting device: 'gfx1031'
ggml_opencl: device FP16 support: true
llama.cpp: loading model from D:\Apps\llama\nous-hermes-llama2-13b.ggmlv3.q4_1.bin
llama_model_load_internal: format     = ggjt v3 (latest)
llama_model_load_internal: n_vocab    = 32032
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 5120
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 40
llama_model_load_internal: n_head_kv  = 40
llama_model_load_internal: n_layer    = 40
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: n_gqa      = 1
llama_model_load_internal: rnorm_eps  = 5.0e-06
llama_model_load_internal: n_ff       = 13824
llama_model_load_internal: freq_base  = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype      = 3 (mostly Q4_1)
llama_model_load_internal: model size = 13B
llama_model_load_internal: ggml ctx size =    0.11 MB
llama_model_load_internal: using OpenCL for GPU acceleration
llama_model_load_internal: mem required  =  195.62 MB (+ 1600.00 MB per state)
llama_model_load_internal: offloading 40 repeating layers to GPU
llama_model_load_internal: offloading non-repeating layers to GPU
llama_model_load_internal: offloaded 41/41 layers to GPU
llama_model_load_internal: total VRAM used: 7565 MB
llama_new_context_with_model: kv self size  = 1600.00 MB
llama_new_context_with_model: compute buffer total size =  191.35 MB

system_info: n_threads = 8 / 16 | AVX = 1 | 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 = 1 | SSE3 = 1 | VSX = 0 |
main: interactive mode on.
Reverse prompt: '### Human:'
Reverse prompt: '### Instruction:

'
sampling: repeat_last_n = 0, repeat_penalty = 1.176471, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.100000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 2048, n_batch = 512, n_predict = -1, n_keep = 2


== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to LLaMa.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.


> can you write an R shiny app to generate a data-frame of 4 columns by 4 rows
library(shiny)

ui <- fluidPage(
  dataTableOutput("my_table")
)

server <- function(input, output) {

  output$my_table <- renderDataTable(data.frame(col1 = 1:4, col2 = 1:4, col3 = 1:4, col4 = 1:4))

}

shinyApp(ui = ui, server = server)

>

llama_print_timings:        load time = 60188.90 ms
llama_print_timings:      sample time =     3.58 ms /   103 runs   (    0.03 ms per token, 28770.95 tokens per second)
llama_print_timings: prompt eval time =  7133.18 ms /    43 tokens (  165.89 ms per token,     6.03 tokens per second)
llama_print_timings:        eval time = 13003.63 ms /   102 runs   (  127.49 ms per token,     7.84 tokens per second)
llama_print_timings:       total time = 622870.10 ms

##################### END DISCRETE ######################
##################### With Integrated GPU Cezanne architecture - gfx1031c

D:\Apps\llama\llama-master-a113689-bin-win-clblast-x64\main.exe -m D:\Apps\llama\nous-hermes-llama2-13b.ggmlv3.q4_1.bin -ngl 50 -i --threads 8 --interactive-first -r "### Human:" --temp 0.7 -c 2048 --top_k 40 --top_p 0.1 --repeat_last_n 0 --repeat_penalty 1.1764705882352942 --instruct
main: build = 929 (a113689)
main: seed  = 1690905475
ggml_opencl: selecting platform: 'AMD Accelerated Parallel Processing'
ggml_opencl: selecting device: 'gfx90c'
ggml_opencl: device FP16 support: true
llama.cpp: loading model from D:\Apps\llama\gpt4all\nous-hermes-llama2-13b.ggmlv3.q4_1.bin
llama_model_load_internal: format     = ggjt v3 (latest)
llama_model_load_internal: n_vocab    = 32032
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 5120
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 40
llama_model_load_internal: n_head_kv  = 40
llama_model_load_internal: n_layer    = 40
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: n_gqa      = 1
llama_model_load_internal: rnorm_eps  = 5.0e-06
llama_model_load_internal: n_ff       = 13824
llama_model_load_internal: freq_base  = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype      = 3 (mostly Q4_1)
llama_model_load_internal: model size = 13B
llama_model_load_internal: ggml ctx size =    0.11 MB
llama_model_load_internal: using OpenCL for GPU acceleration
llama_model_load_internal: mem required  =  195.62 MB (+ 1600.00 MB per state)
llama_model_load_internal: offloading 40 repeating layers to GPU
llama_model_load_internal: offloading non-repeating layers to GPU
llama_model_load_internal: offloaded 41/41 layers to GPU
llama_model_load_internal: total VRAM used: 7565 MB
llama_new_context_with_model: kv self size  = 1600.00 MB
llama_new_context_with_model: compute buffer total size =  191.35 MB

system_info: n_threads = 8 / 16 | AVX = 1 | 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 = 1 | SSE3 = 1 | VSX = 0 |
main: interactive mode on.
Reverse prompt: '### Human:'
Reverse prompt: '### Instruction:

'
sampling: repeat_last_n = 0, repeat_penalty = 1.176471, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.100000, typical_p = 1.000000, temp = 0.700000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 2048, n_batch = 512, n_predict = -1, n_keep = 2


== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to LLaMa.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.


> can you write an R shiny app to generate a data-frame of 4 columns by 4 rows
library(shiny)

ui <- fluidPage(
  dataTableOutput("my_table")
)

server <- function(input, output) {

  output$my_table <- renderDataTable(data.frame(col1 = 1:4, col2 = 1:4, col3 = 1:4, col4 = 1:4))

}

shinyApp(ui = ui, server = server)

>

llama_print_timings:        load time = 26205.90 ms
llama_print_timings:      sample time =     6.34 ms /   103 runs   (    0.06 ms per token, 16235.81 tokens per second)
llama_print_timings: prompt eval time = 29234.08 ms /    43 tokens (  679.86 ms per token,     1.47 tokens per second)
llama_print_timings:        eval time = 118847.32 ms /   102 runs   ( 1165.17 ms per token,     0.86 tokens per second)
llama_print_timings:       total time = 159929.10 ms

################### END INTEGRATED ##################