how to disable f16memory and keep the memory within the llama.cpp settings? i'm oom ed with go-llama as below

[hiqsociety]

@mudler

llama.cpp

llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q3_K:  281 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_print_meta: format         = GGUF V2 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32000
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 4096
llm_load_print_meta: n_ctx          = 1920
llm_load_print_meta: n_embd         = 5120
llm_load_print_meta: n_head         = 40
llm_load_print_meta: n_head_kv      = 40
llm_load_print_meta: n_layer        = 40
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
llm_load_print_meta: f_norm_eps     = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: n_ff           = 13824
llm_load_print_meta: freq_base      = 10000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 13B
llm_load_print_meta: model ftype    = mostly Q3_K - Small
llm_load_print_meta: model size     = 13.02 B
llm_load_print_meta: general.name   = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.12 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required  =   67.25 MB (+ 1500.00 MB per state)
llm_load_tensors: offloading 40 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloading v cache to GPU
llm_load_tensors: offloading k cache to GPU
llm_load_tensors: offloaded 43/43 layers to GPU
llm_load_tensors: VRAM used: 6829 MB
...................................................................................................
llama_new_context_with_model: kv self size  = 1500.00 MB
llama_new_context_with_model: compute buffer total size =    1.82 MB
llama_new_context_with_model: VRAM scratch buffer: 0.35 MB

system_info: n_threads = 12 / 12 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.300000, mirostat = 2, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 1920, n_batch = 1, n_predict = 1920, n_keep = 0

go-llama.cpp

llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q3_K:  281 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_print_meta: format         = GGUF V2 (latest)
llm_load_print_meta: arch           = llama
llm_load_print_meta: vocab type     = SPM
llm_load_print_meta: n_vocab        = 32000
llm_load_print_meta: n_merges       = 0
llm_load_print_meta: n_ctx_train    = 4096
llm_load_print_meta: n_ctx          = 512
llm_load_print_meta: n_embd         = 5120
llm_load_print_meta: n_head         = 40
llm_load_print_meta: n_head_kv      = 40
llm_load_print_meta: n_layer        = 40
llm_load_print_meta: n_rot          = 128
llm_load_print_meta: n_gqa          = 1
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: n_ff           = 13824
llm_load_print_meta: freq_base      = 10000.0
llm_load_print_meta: freq_scale     = 1
llm_load_print_meta: model type     = 13B
llm_load_print_meta: model ftype    = mostly Q3_K - Small
llm_load_print_meta: model params   = 13.02 B
llm_load_print_meta: model size     = 5.27 GiB (3.48 BPW) 
llm_load_print_meta: general.name   = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.12 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required  =   67.25 MB (+  800.00 MB per state)
llm_load_tensors: offloading 40 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloading v cache to GPU
llm_load_tensors: offloading k cache to GPU
llm_load_tensors: offloaded 43/43 layers to GPU
llm_load_tensors: VRAM used: 5729 MB
...................................................................................................
llama_new_context_with_model: kv self size  =  800.00 MB
llama_new_context_with_model: compute buffer total size =    1.61 MB
llama_new_context_with_model: VRAM scratch buffer: 0.14 MB
GGML_ASSERT: /usr/local/src/go-llama.cpp/llama.cpp/ggml-cuda.cu:6642: src0->type == GGML_TYPE_F16
SIGABRT: abort
PC=0x7fa565c96a7c m=0 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 1 [syscall]: