nous-hermes and parameters #80

Closed
opened 2025-11-12 09:10:55 -06:00 by GiteaMirror · 4 comments
Owner

Originally created by @alivardar on GitHub (Jul 24, 2023).

Hello,
If I want to generate my model, this example with temperature and num_ctx paramters crashing "ollama" application.

FROM nous-hermes

sets the temperature to 1 [higher is more creative, lower is more coherent]

sets the context size to 4096

PARAMETER temperature 2
PARAMETER num_ctx 4096

Here is all result when app crashed.

alivardar@Alis-MacBook-Air ModelFiles % ollama serve
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.

  • using env: export GIN_MODE=release
  • using code: gin.SetMode(gin.ReleaseMode)

[GIN-debug] GET / --> github.com/jmorganca/ollama/server.Serve.func1 (3 handlers)
[GIN-debug] POST /api/pull --> github.com/jmorganca/ollama/server.PullModelHandler (3 handlers)
[GIN-debug] POST /api/generate --> github.com/jmorganca/ollama/server.GenerateHandler (3 handlers)
[GIN-debug] POST /api/create --> github.com/jmorganca/ollama/server.CreateModelHandler (3 handlers)
[GIN-debug] POST /api/push --> github.com/jmorganca/ollama/server.PushModelHandler (3 handlers)
[GIN-debug] GET /api/tags --> github.com/jmorganca/ollama/server.ListModelsHandler (3 handlers)
[GIN-debug] DELETE /api/delete --> github.com/jmorganca/ollama/server.DeleteModelHandler (3 handlers)
2023/07/24 22:54:48 routes.go:237: Listening on 127.0.0.1:11434
llama.cpp: loading model from /Users/alivardar/.ollama/models/blobs/sha256:d1735b93e1dc503f1045ccd6c8bd73277b18ba892befd1dc29e9b9a7822ed998
llama_model_load_internal: format = ggjt v3 (latest)
llama_model_load_internal: n_vocab = 32001
llama_model_load_internal: n_ctx = 4096
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_layer = 40
llama_model_load_internal: n_rot = 128
llama_model_load_internal: freq_base = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype = 2 (mostly Q4_0)
llama_model_load_internal: n_ff = 13824
llama_model_load_internal: model size = 13B
llama_model_load_internal: ggml ctx size = 0.09 MB
llama_model_load_internal: mem required = 9132.72 MB (+ 1608.00 MB per state)
llama_new_context_with_model: kv self size = 3200.00 MB
ggml_metal_init: allocating
ggml_metal_init: using MPS
ggml_metal_init: loading '/Applications/Ollama.app/Contents/Resources/ggml-metal.metal'
ggml_metal_init: loaded kernel_add 0x152f0a280
ggml_metal_init: loaded kernel_mul 0x152f0a880
ggml_metal_init: loaded kernel_mul_row 0x152f0aeb0
ggml_metal_init: loaded kernel_scale 0x152f0b3d0
ggml_metal_init: loaded kernel_silu 0x152f0b8f0
ggml_metal_init: loaded kernel_relu 0x152f0be10
ggml_metal_init: loaded kernel_gelu 0x152f0c330
ggml_metal_init: loaded kernel_soft_max 0x152f0c9e0
ggml_metal_init: loaded kernel_diag_mask_inf 0x152f0d040
ggml_metal_init: loaded kernel_get_rows_f16 0x152f0d6c0
ggml_metal_init: loaded kernel_get_rows_q4_0 0x152f0dd40
ggml_metal_init: loaded kernel_get_rows_q4_1 0x152f0e530
ggml_metal_init: loaded kernel_get_rows_q2_K 0x152f0ebb0
ggml_metal_init: loaded kernel_get_rows_q3_K 0x152f0f230
ggml_metal_init: loaded kernel_get_rows_q4_K 0x152f0f8b0
ggml_metal_init: loaded kernel_get_rows_q5_K 0x152f0ff30
ggml_metal_init: loaded kernel_get_rows_q6_K 0x152f105b0
ggml_metal_init: loaded kernel_rms_norm 0x152f10c70
ggml_metal_init: loaded kernel_norm 0x152f11320
ggml_metal_init: loaded kernel_mul_mat_f16_f32 0x152f11cf0
ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x152f123b0
ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x152f12a70
ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x152f13150
ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x152f139d0
ggml_metal_init: loaded kernel_mul_mat_q4_K_f32 0x152f14090
ggml_metal_init: loaded kernel_mul_mat_q5_K_f32 0x152f14730
ggml_metal_init: loaded kernel_mul_mat_q6_K_f32 0x152f14dd0
ggml_metal_init: loaded kernel_rope 0x152f154f0
ggml_metal_init: loaded kernel_alibi_f32 0x152f16010
ggml_metal_init: loaded kernel_cpy_f32_f16 0x152f168a0
ggml_metal_init: loaded kernel_cpy_f32_f32 0x152f17130
ggml_metal_init: loaded kernel_cpy_f16_f16 0x152f179c0
ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: maxTransferRate = built-in GPU
llama_new_context_with_model: max tensor size = 87.89 MB
ggml_metal_add_buffer: allocated 'data ' buffer, size = 6984.06 MB, ( 6984.52 / 10922.67)
ggml_metal_add_buffer: allocated 'eval ' buffer, size = 1040.00 MB, ( 8024.52 / 10922.67)
ggml_metal_add_buffer: allocated 'kv ' buffer, size = 3202.00 MB, (11226.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size
ggml_metal_add_buffer: allocated 'scr0 ' buffer, size = 597.00 MB, (11823.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size
ggml_metal_add_buffer: allocated 'scr1 ' buffer, size = 512.00 MB, (12335.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size
ggml_metal_graph_compute: command buffer 0 failed with status 5
GGML_ASSERT: ggml-metal.m:1023: false
SIGABRT: abort
PC=0x1a1500724 m=5 sigcode=0
signal arrived during cgo execution

goroutine 19 [syscall]:
runtime.cgocall(0x102d99e8c, 0x1400018d278)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/cgocall.go:157 +0x54 fp=0x1400018d240 sp=0x1400018d200 pc=0x102888c64
github.com/jmorganca/ollama/llama._Cfunc_llama_eval(0x153813c00, 0x14000471e28, 0x1, 0x0, 0x8)
_cgo_gotypes.go:210 +0x38 fp=0x1400018d270 sp=0x1400018d240 pc=0x102d87448
github.com/jmorganca/ollama/llama.New.func4(0x102fc2de0?, {0x14000471e28, 0x1, 0x0?}, {0xffffffffffffffff, 0x0, 0x1000, 0x200, 0x1, 0x0, ...})
/Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x7c fp=0x1400018d2c0 sp=0x1400018d270 pc=0x102d8826c
github.com/jmorganca/ollama/llama.New({0x1400028ce00, 0x6d}, {0xffffffffffffffff, 0x0, 0x1000, 0x200, 0x1, 0x0, 0x0, 0x1, ...})
/Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x288 fp=0x1400018d480 sp=0x1400018d2c0 pc=0x102d88028
github.com/jmorganca/ollama/server.GenerateHandler(0x14000498300)
/Users/jmorgan/workspace/ollama/server/routes.go:54 +0x5c0 fp=0x1400018d6e0 sp=0x1400018d480 pc=0x102d939f0
github.com/gin-gonic/gin.(*Context).Next(...)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0x14000498300)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 +0x7c fp=0x1400018d730 sp=0x1400018d6e0 pc=0x102d7eb3c
github.com/gin-gonic/gin.(*Context).Next(...)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.LoggerWithConfig.func1(0x14000498300)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 +0xac fp=0x1400018d8e0 sp=0x1400018d730 pc=0x102d7ddbc
github.com/gin-gonic/gin.(*Context).Next(...)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174
github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0x1400047a820, 0x14000498300)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 +0x54c fp=0x1400018da70 sp=0x1400018d8e0 pc=0x102d7cecc
github.com/gin-gonic/gin.(*Engine).ServeHTTP(0x1400047a820, {0x103014f10?, 0x14000443420}, 0x14000498200)
/Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 +0x1d4 fp=0x1400018dab0 sp=0x1400018da70 pc=0x102d7c7d4
net/http.serverHandler.ServeHTTP({0x103012e70?}, {0x103014f10, 0x14000443420}, 0x14000498200)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:2936 +0x2d8 fp=0x1400018db60 sp=0x1400018dab0 pc=0x102b06408
net/http.(*conn).serve(0x140001a0900, {0x103015588, 0x1400049a060})
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:1995 +0x560 fp=0x1400018dfa0 sp=0x1400018db60 pc=0x102b02100
net/http.(*Server).Serve.func3()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x30 fp=0x1400018dfd0 sp=0x1400018dfa0 pc=0x102b06c30
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x1400018dfd0 sp=0x1400018dfd0 pc=0x1028ec074
created by net/http.(*Server).Serve
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x520

goroutine 1 [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000337860 sp=0x14000337840 pc=0x1028bbee4
runtime.netpollblock(0x140003378f8?, 0x296fca4?, 0x1?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x140003378a0 sp=0x14000337860 pc=0x1028b5408
internal/poll.runtime_pollWait(0x12aae7a18, 0x72)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x140003378d0 sp=0x140003378a0 pc=0x1028e5c40
internal/poll.(*pollDesc).wait(0x14000478600?, 0x0?, 0x0)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000337900 sp=0x140003378d0 pc=0x10296b2e8
internal/poll.(*pollDesc).waitRead(...)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x14000478600)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:614 +0x250 fp=0x140003379b0 sp=0x14000337900 pc=0x10296fd90
net.(*netFD).accept(0x14000478600)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_unix.go:172 +0x28 fp=0x14000337a70 sp=0x140003379b0 pc=0x1029af2f8
net.(*TCPListener).accept(0x1400012ed68)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock_posix.go:148 +0x28 fp=0x14000337aa0 sp=0x14000337a70 pc=0x1029c48f8
net.(*TCPListener).Accept(0x1400012ed68)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock.go:297 +0x2c fp=0x14000337ae0 sp=0x14000337aa0 pc=0x1029c3a6c
net/http.(*onceCloseListener).Accept(0x140001a0900?)
:1 +0x30 fp=0x14000337b00 sp=0x14000337ae0 pc=0x102b2a3b0
net/http.(*Server).Serve(0x1400039cff0, {0x103014d00, 0x1400012ed68})
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3059 +0x304 fp=0x14000337c30 sp=0x14000337b00 pc=0x102b068d4
github.com/jmorganca/ollama/server.Serve({0x103014d00, 0x1400012ed68})
/Users/jmorgan/workspace/ollama/server/routes.go:242 +0x294 fp=0x14000337ca0 sp=0x14000337c30 pc=0x102d95aa4
github.com/jmorganca/ollama/cmd.RunServer(0x14000449200?, {0x102deac46?, 0x0?, 0x0?})
/Users/jmorgan/workspace/ollama/cmd/cmd.go:384 +0x114 fp=0x14000337d20 sp=0x14000337ca0 pc=0x102d98ea4
github.com/spf13/cobra.(*Command).execute(0x14000449200, {0x10348e290, 0x0, 0x0})
/Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x5c8 fp=0x14000337e60 sp=0x14000337d20 pc=0x102bacb18
github.com/spf13/cobra.(*Command).ExecuteC(0x14000448900)
/Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x35c fp=0x14000337f20 sp=0x14000337e60 pc=0x102bad26c
github.com/spf13/cobra.(*Command).Execute(...)
/Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(0x14000054768?, {0x103015518?, 0x14000120010?})
/Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 +0x50 fp=0x14000337f40 sp=0x14000337f20 pc=0x102bace00
main.main()
/Users/jmorgan/workspace/ollama/main.go:10 +0x34 fp=0x14000337f70 sp=0x14000337f40 pc=0x102d99c54
runtime.main()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:250 +0x248 fp=0x14000337fd0 sp=0x14000337f70 pc=0x1028bbab8
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000337fd0 sp=0x14000337fd0 pc=0x1028ec074

goroutine 2 [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054fa0 sp=0x14000054f80 pc=0x1028bbee4
runtime.goparkunlock(...)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387
runtime.forcegchelper()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:305 +0xb8 fp=0x14000054fd0 sp=0x14000054fa0 pc=0x1028bbd28
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000054fd0 sp=0x14000054fd0 pc=0x1028ec074
created by runtime.init.6
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:293 +0x24

goroutine 3 [GC sweep wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055760 sp=0x14000055740 pc=0x1028bbee4
runtime.goparkunlock(...)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387
runtime.bgsweep(0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcsweep.go:278 +0xa4 fp=0x140000557b0 sp=0x14000055760 pc=0x1028a8bc4
runtime.gcenable.func1()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x28 fp=0x140000557d0 sp=0x140000557b0 pc=0x10289d6d8
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000557d0 sp=0x140000557d0 pc=0x1028ec074
created by runtime.gcenable
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x74

goroutine 4 [GC scavenge wait]:
runtime.gopark(0x1400007c000?, 0x102ee86e8?, 0x1?, 0x0?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055f50 sp=0x14000055f30 pc=0x1028bbee4
runtime.goparkunlock(...)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387
runtime.(*scavengerState).park(0x1033d2d60)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:400 +0x5c fp=0x14000055f80 sp=0x14000055f50 pc=0x1028a6a3c
runtime.bgscavenge(0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:628 +0x44 fp=0x14000055fb0 sp=0x14000055f80 pc=0x1028a6fb4
runtime.gcenable.func2()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0x28 fp=0x14000055fd0 sp=0x14000055fb0 pc=0x10289d678
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000055fd0 sp=0x14000055fd0 pc=0x1028ec074
created by runtime.gcenable
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0xb8

goroutine 18 [finalizer wait]:
runtime.gopark(0x1a0?, 0x1033d37a0?, 0x40?, 0x23?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054580 sp=0x14000054560 pc=0x1028bbee4
runtime.runfinq()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:193 +0x10c fp=0x140000547d0 sp=0x14000054580 pc=0x10289c76c
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000547d0 sp=0x140000547d0 pc=0x1028ec074
created by runtime.createfing
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:163 +0x84

goroutine 20 [IO wait]:
runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x1028fe890?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000050540 sp=0x14000050520 pc=0x1028bbee4
runtime.netpollblock(0x0?, 0x0?, 0x0?)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000050580 sp=0x14000050540 pc=0x1028b5408
internal/poll.runtime_pollWait(0x12aae7928, 0x72)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x140000505b0 sp=0x14000050580 pc=0x1028e5c40
internal/poll.(*pollDesc).wait(0x14000478680?, 0x1400049a161?, 0x0)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140000505e0 sp=0x140000505b0 pc=0x10296b2e8
internal/poll.(*pollDesc).waitRead(...)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x14000478680, {0x1400049a161, 0x1, 0x1})
/opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:167 +0x200 fp=0x14000050680 sp=0x140000505e0 pc=0x10296c650
net.(*netFD).Read(0x14000478680, {0x1400049a161?, 0x0?, 0x0?})
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_posix.go:55 +0x28 fp=0x140000506d0 sp=0x14000050680 pc=0x1029ad658
net.(*conn).Read(0x14000130d00, {0x1400049a161?, 0x0?, 0x0?})
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/net.go:183 +0x34 fp=0x14000050720 sp=0x140000506d0 pc=0x1029bbc64
net.(*TCPConn).Read(0x0?, {0x1400049a161?, 0x0?, 0x0?})
:1 +0x2c fp=0x14000050750 sp=0x14000050720 pc=0x1029ce1ac
net/http.(*connReader).backgroundRead(0x1400049a150)
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:674 +0x44 fp=0x140000507b0 sp=0x14000050750 pc=0x102afc5b4
net/http.(*connReader).startBackgroundRead.func2()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0x28 fp=0x140000507d0 sp=0x140000507b0 pc=0x102afc4d8
runtime.goexit()
/opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000507d0 sp=0x140000507d0 pc=0x1028ec074
created by net/http.(*connReader).startBackgroundRead
/opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0xcc

r0 0x0
r1 0x0
r2 0x0
r3 0x0
r4 0x0
r5 0x16f586c00
r6 0xa
r7 0x0
r8 0xe035c4e8feb62ded
r9 0xe035c4e991efdded
r10 0x2
r11 0xfffffffd
r12 0x10000000000
r13 0x0
r14 0x0
r15 0x0
r16 0x148
r17 0x201034f60
r18 0x0
r19 0x6
r20 0x16f59f000
r21 0x1603
r22 0x16f59f0e0
r23 0x8
r24 0x7
r25 0x8
r26 0x1fc513720
r27 0x102ddb9c0
r28 0x102f010f0
r29 0x16f586bb0
lr 0x1a1537c28
sp 0x16f586b90
pc 0x1a1500724
fault 0x1a1500724

Originally created by @alivardar on GitHub (Jul 24, 2023). Hello, If I want to generate my model, this example with temperature and num_ctx paramters crashing "ollama" application. FROM nous-hermes # sets the temperature to 1 [higher is more creative, lower is more coherent] # sets the context size to 4096 PARAMETER temperature 2 PARAMETER num_ctx 4096 Here is all result when app crashed. alivardar@Alis-MacBook-Air ModelFiles % ollama serve [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached. [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production. - using env: export GIN_MODE=release - using code: gin.SetMode(gin.ReleaseMode) [GIN-debug] GET / --> github.com/jmorganca/ollama/server.Serve.func1 (3 handlers) [GIN-debug] POST /api/pull --> github.com/jmorganca/ollama/server.PullModelHandler (3 handlers) [GIN-debug] POST /api/generate --> github.com/jmorganca/ollama/server.GenerateHandler (3 handlers) [GIN-debug] POST /api/create --> github.com/jmorganca/ollama/server.CreateModelHandler (3 handlers) [GIN-debug] POST /api/push --> github.com/jmorganca/ollama/server.PushModelHandler (3 handlers) [GIN-debug] GET /api/tags --> github.com/jmorganca/ollama/server.ListModelsHandler (3 handlers) [GIN-debug] DELETE /api/delete --> github.com/jmorganca/ollama/server.DeleteModelHandler (3 handlers) 2023/07/24 22:54:48 routes.go:237: Listening on 127.0.0.1:11434 llama.cpp: loading model from /Users/alivardar/.ollama/models/blobs/sha256:d1735b93e1dc503f1045ccd6c8bd73277b18ba892befd1dc29e9b9a7822ed998 llama_model_load_internal: format = ggjt v3 (latest) llama_model_load_internal: n_vocab = 32001 llama_model_load_internal: n_ctx = 4096 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_layer = 40 llama_model_load_internal: n_rot = 128 llama_model_load_internal: freq_base = 10000.0 llama_model_load_internal: freq_scale = 1 llama_model_load_internal: ftype = 2 (mostly Q4_0) llama_model_load_internal: n_ff = 13824 llama_model_load_internal: model size = 13B llama_model_load_internal: ggml ctx size = 0.09 MB llama_model_load_internal: mem required = 9132.72 MB (+ 1608.00 MB per state) llama_new_context_with_model: kv self size = 3200.00 MB ggml_metal_init: allocating ggml_metal_init: using MPS ggml_metal_init: loading '/Applications/Ollama.app/Contents/Resources/ggml-metal.metal' ggml_metal_init: loaded kernel_add 0x152f0a280 ggml_metal_init: loaded kernel_mul 0x152f0a880 ggml_metal_init: loaded kernel_mul_row 0x152f0aeb0 ggml_metal_init: loaded kernel_scale 0x152f0b3d0 ggml_metal_init: loaded kernel_silu 0x152f0b8f0 ggml_metal_init: loaded kernel_relu 0x152f0be10 ggml_metal_init: loaded kernel_gelu 0x152f0c330 ggml_metal_init: loaded kernel_soft_max 0x152f0c9e0 ggml_metal_init: loaded kernel_diag_mask_inf 0x152f0d040 ggml_metal_init: loaded kernel_get_rows_f16 0x152f0d6c0 ggml_metal_init: loaded kernel_get_rows_q4_0 0x152f0dd40 ggml_metal_init: loaded kernel_get_rows_q4_1 0x152f0e530 ggml_metal_init: loaded kernel_get_rows_q2_K 0x152f0ebb0 ggml_metal_init: loaded kernel_get_rows_q3_K 0x152f0f230 ggml_metal_init: loaded kernel_get_rows_q4_K 0x152f0f8b0 ggml_metal_init: loaded kernel_get_rows_q5_K 0x152f0ff30 ggml_metal_init: loaded kernel_get_rows_q6_K 0x152f105b0 ggml_metal_init: loaded kernel_rms_norm 0x152f10c70 ggml_metal_init: loaded kernel_norm 0x152f11320 ggml_metal_init: loaded kernel_mul_mat_f16_f32 0x152f11cf0 ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x152f123b0 ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x152f12a70 ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x152f13150 ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x152f139d0 ggml_metal_init: loaded kernel_mul_mat_q4_K_f32 0x152f14090 ggml_metal_init: loaded kernel_mul_mat_q5_K_f32 0x152f14730 ggml_metal_init: loaded kernel_mul_mat_q6_K_f32 0x152f14dd0 ggml_metal_init: loaded kernel_rope 0x152f154f0 ggml_metal_init: loaded kernel_alibi_f32 0x152f16010 ggml_metal_init: loaded kernel_cpy_f32_f16 0x152f168a0 ggml_metal_init: loaded kernel_cpy_f32_f32 0x152f17130 ggml_metal_init: loaded kernel_cpy_f16_f16 0x152f179c0 ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: maxTransferRate = built-in GPU llama_new_context_with_model: max tensor size = 87.89 MB ggml_metal_add_buffer: allocated 'data ' buffer, size = 6984.06 MB, ( 6984.52 / 10922.67) ggml_metal_add_buffer: allocated 'eval ' buffer, size = 1040.00 MB, ( 8024.52 / 10922.67) ggml_metal_add_buffer: allocated 'kv ' buffer, size = 3202.00 MB, (11226.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size ggml_metal_add_buffer: allocated 'scr0 ' buffer, size = 597.00 MB, (11823.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size ggml_metal_add_buffer: allocated 'scr1 ' buffer, size = 512.00 MB, (12335.52 / 10922.67), warning: current allocated size is greater than the recommended max working set size ggml_metal_graph_compute: command buffer 0 failed with status 5 GGML_ASSERT: ggml-metal.m:1023: false SIGABRT: abort PC=0x1a1500724 m=5 sigcode=0 signal arrived during cgo execution goroutine 19 [syscall]: runtime.cgocall(0x102d99e8c, 0x1400018d278) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/cgocall.go:157 +0x54 fp=0x1400018d240 sp=0x1400018d200 pc=0x102888c64 github.com/jmorganca/ollama/llama._Cfunc_llama_eval(0x153813c00, 0x14000471e28, 0x1, 0x0, 0x8) _cgo_gotypes.go:210 +0x38 fp=0x1400018d270 sp=0x1400018d240 pc=0x102d87448 github.com/jmorganca/ollama/llama.New.func4(0x102fc2de0?, {0x14000471e28, 0x1, 0x0?}, {0xffffffffffffffff, 0x0, 0x1000, 0x200, 0x1, 0x0, ...}) /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x7c fp=0x1400018d2c0 sp=0x1400018d270 pc=0x102d8826c github.com/jmorganca/ollama/llama.New({0x1400028ce00, 0x6d}, {0xffffffffffffffff, 0x0, 0x1000, 0x200, 0x1, 0x0, 0x0, 0x1, ...}) /Users/jmorgan/workspace/ollama/llama/llama.go:141 +0x288 fp=0x1400018d480 sp=0x1400018d2c0 pc=0x102d88028 github.com/jmorganca/ollama/server.GenerateHandler(0x14000498300) /Users/jmorgan/workspace/ollama/server/routes.go:54 +0x5c0 fp=0x1400018d6e0 sp=0x1400018d480 pc=0x102d939f0 github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.CustomRecoveryWithWriter.func1(0x14000498300) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/recovery.go:102 +0x7c fp=0x1400018d730 sp=0x1400018d6e0 pc=0x102d7eb3c github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.LoggerWithConfig.func1(0x14000498300) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/logger.go:240 +0xac fp=0x1400018d8e0 sp=0x1400018d730 pc=0x102d7ddbc github.com/gin-gonic/gin.(*Context).Next(...) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/context.go:174 github.com/gin-gonic/gin.(*Engine).handleHTTPRequest(0x1400047a820, 0x14000498300) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:620 +0x54c fp=0x1400018da70 sp=0x1400018d8e0 pc=0x102d7cecc github.com/gin-gonic/gin.(*Engine).ServeHTTP(0x1400047a820, {0x103014f10?, 0x14000443420}, 0x14000498200) /Users/jmorgan/go/pkg/mod/github.com/gin-gonic/gin@v1.9.1/gin.go:576 +0x1d4 fp=0x1400018dab0 sp=0x1400018da70 pc=0x102d7c7d4 net/http.serverHandler.ServeHTTP({0x103012e70?}, {0x103014f10, 0x14000443420}, 0x14000498200) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:2936 +0x2d8 fp=0x1400018db60 sp=0x1400018dab0 pc=0x102b06408 net/http.(*conn).serve(0x140001a0900, {0x103015588, 0x1400049a060}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:1995 +0x560 fp=0x1400018dfa0 sp=0x1400018db60 pc=0x102b02100 net/http.(*Server).Serve.func3() /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x30 fp=0x1400018dfd0 sp=0x1400018dfa0 pc=0x102b06c30 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x1400018dfd0 sp=0x1400018dfd0 pc=0x1028ec074 created by net/http.(*Server).Serve /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3089 +0x520 goroutine 1 [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000337860 sp=0x14000337840 pc=0x1028bbee4 runtime.netpollblock(0x140003378f8?, 0x296fca4?, 0x1?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x140003378a0 sp=0x14000337860 pc=0x1028b5408 internal/poll.runtime_pollWait(0x12aae7a18, 0x72) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x140003378d0 sp=0x140003378a0 pc=0x1028e5c40 internal/poll.(*pollDesc).wait(0x14000478600?, 0x0?, 0x0) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000337900 sp=0x140003378d0 pc=0x10296b2e8 internal/poll.(*pollDesc).waitRead(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x14000478600) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:614 +0x250 fp=0x140003379b0 sp=0x14000337900 pc=0x10296fd90 net.(*netFD).accept(0x14000478600) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_unix.go:172 +0x28 fp=0x14000337a70 sp=0x140003379b0 pc=0x1029af2f8 net.(*TCPListener).accept(0x1400012ed68) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock_posix.go:148 +0x28 fp=0x14000337aa0 sp=0x14000337a70 pc=0x1029c48f8 net.(*TCPListener).Accept(0x1400012ed68) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/tcpsock.go:297 +0x2c fp=0x14000337ae0 sp=0x14000337aa0 pc=0x1029c3a6c net/http.(*onceCloseListener).Accept(0x140001a0900?) <autogenerated>:1 +0x30 fp=0x14000337b00 sp=0x14000337ae0 pc=0x102b2a3b0 net/http.(*Server).Serve(0x1400039cff0, {0x103014d00, 0x1400012ed68}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:3059 +0x304 fp=0x14000337c30 sp=0x14000337b00 pc=0x102b068d4 github.com/jmorganca/ollama/server.Serve({0x103014d00, 0x1400012ed68}) /Users/jmorgan/workspace/ollama/server/routes.go:242 +0x294 fp=0x14000337ca0 sp=0x14000337c30 pc=0x102d95aa4 github.com/jmorganca/ollama/cmd.RunServer(0x14000449200?, {0x102deac46?, 0x0?, 0x0?}) /Users/jmorgan/workspace/ollama/cmd/cmd.go:384 +0x114 fp=0x14000337d20 sp=0x14000337ca0 pc=0x102d98ea4 github.com/spf13/cobra.(*Command).execute(0x14000449200, {0x10348e290, 0x0, 0x0}) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x5c8 fp=0x14000337e60 sp=0x14000337d20 pc=0x102bacb18 github.com/spf13/cobra.(*Command).ExecuteC(0x14000448900) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x35c fp=0x14000337f20 sp=0x14000337e60 pc=0x102bad26c github.com/spf13/cobra.(*Command).Execute(...) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(0x14000054768?, {0x103015518?, 0x14000120010?}) /Users/jmorgan/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 +0x50 fp=0x14000337f40 sp=0x14000337f20 pc=0x102bace00 main.main() /Users/jmorgan/workspace/ollama/main.go:10 +0x34 fp=0x14000337f70 sp=0x14000337f40 pc=0x102d99c54 runtime.main() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:250 +0x248 fp=0x14000337fd0 sp=0x14000337f70 pc=0x1028bbab8 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000337fd0 sp=0x14000337fd0 pc=0x1028ec074 goroutine 2 [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054fa0 sp=0x14000054f80 pc=0x1028bbee4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387 runtime.forcegchelper() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:305 +0xb8 fp=0x14000054fd0 sp=0x14000054fa0 pc=0x1028bbd28 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000054fd0 sp=0x14000054fd0 pc=0x1028ec074 created by runtime.init.6 /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:293 +0x24 goroutine 3 [GC sweep wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055760 sp=0x14000055740 pc=0x1028bbee4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387 runtime.bgsweep(0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcsweep.go:278 +0xa4 fp=0x140000557b0 sp=0x14000055760 pc=0x1028a8bc4 runtime.gcenable.func1() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x28 fp=0x140000557d0 sp=0x140000557b0 pc=0x10289d6d8 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000557d0 sp=0x140000557d0 pc=0x1028ec074 created by runtime.gcenable /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:178 +0x74 goroutine 4 [GC scavenge wait]: runtime.gopark(0x1400007c000?, 0x102ee86e8?, 0x1?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000055f50 sp=0x14000055f30 pc=0x1028bbee4 runtime.goparkunlock(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:387 runtime.(*scavengerState).park(0x1033d2d60) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:400 +0x5c fp=0x14000055f80 sp=0x14000055f50 pc=0x1028a6a3c runtime.bgscavenge(0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgcscavenge.go:628 +0x44 fp=0x14000055fb0 sp=0x14000055f80 pc=0x1028a6fb4 runtime.gcenable.func2() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0x28 fp=0x14000055fd0 sp=0x14000055fb0 pc=0x10289d678 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x14000055fd0 sp=0x14000055fd0 pc=0x1028ec074 created by runtime.gcenable /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mgc.go:179 +0xb8 goroutine 18 [finalizer wait]: runtime.gopark(0x1a0?, 0x1033d37a0?, 0x40?, 0x23?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000054580 sp=0x14000054560 pc=0x1028bbee4 runtime.runfinq() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:193 +0x10c fp=0x140000547d0 sp=0x14000054580 pc=0x10289c76c runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000547d0 sp=0x140000547d0 pc=0x1028ec074 created by runtime.createfing /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/mfinal.go:163 +0x84 goroutine 20 [IO wait]: runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x1028fe890?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/proc.go:381 +0xe4 fp=0x14000050540 sp=0x14000050520 pc=0x1028bbee4 runtime.netpollblock(0x0?, 0x0?, 0x0?) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:527 +0x158 fp=0x14000050580 sp=0x14000050540 pc=0x1028b5408 internal/poll.runtime_pollWait(0x12aae7928, 0x72) /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/netpoll.go:306 +0xa0 fp=0x140000505b0 sp=0x14000050580 pc=0x1028e5c40 internal/poll.(*pollDesc).wait(0x14000478680?, 0x1400049a161?, 0x0) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140000505e0 sp=0x140000505b0 pc=0x10296b2e8 internal/poll.(*pollDesc).waitRead(...) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x14000478680, {0x1400049a161, 0x1, 0x1}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/internal/poll/fd_unix.go:167 +0x200 fp=0x14000050680 sp=0x140000505e0 pc=0x10296c650 net.(*netFD).Read(0x14000478680, {0x1400049a161?, 0x0?, 0x0?}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/fd_posix.go:55 +0x28 fp=0x140000506d0 sp=0x14000050680 pc=0x1029ad658 net.(*conn).Read(0x14000130d00, {0x1400049a161?, 0x0?, 0x0?}) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/net.go:183 +0x34 fp=0x14000050720 sp=0x140000506d0 pc=0x1029bbc64 net.(*TCPConn).Read(0x0?, {0x1400049a161?, 0x0?, 0x0?}) <autogenerated>:1 +0x2c fp=0x14000050750 sp=0x14000050720 pc=0x1029ce1ac net/http.(*connReader).backgroundRead(0x1400049a150) /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:674 +0x44 fp=0x140000507b0 sp=0x14000050750 pc=0x102afc5b4 net/http.(*connReader).startBackgroundRead.func2() /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0x28 fp=0x140000507d0 sp=0x140000507b0 pc=0x102afc4d8 runtime.goexit() /opt/homebrew/Cellar/go/1.20.5/libexec/src/runtime/asm_arm64.s:1172 +0x4 fp=0x140000507d0 sp=0x140000507d0 pc=0x1028ec074 created by net/http.(*connReader).startBackgroundRead /opt/homebrew/Cellar/go/1.20.5/libexec/src/net/http/server.go:670 +0xcc r0 0x0 r1 0x0 r2 0x0 r3 0x0 r4 0x0 r5 0x16f586c00 r6 0xa r7 0x0 r8 0xe035c4e8feb62ded r9 0xe035c4e991efdded r10 0x2 r11 0xfffffffd r12 0x10000000000 r13 0x0 r14 0x0 r15 0x0 r16 0x148 r17 0x201034f60 r18 0x0 r19 0x6 r20 0x16f59f000 r21 0x1603 r22 0x16f59f0e0 r23 0x8 r24 0x7 r25 0x8 r26 0x1fc513720 r27 0x102ddb9c0 r28 0x102f010f0 r29 0x16f586bb0 lr 0x1a1537c28 sp 0x16f586b90 pc 0x1a1500724 fault 0x1a1500724
GiteaMirror added the bug label 2025-11-12 09:10:55 -06:00
Author
Owner

@radiofreejohn commented on GitHub (Jul 25, 2023):

Are you sure you're not running out of memory? The assertion failure there looks like a check for available memory. I was able to build and run a model with nous-hermes and temperature 2 num_ctx 4096 on a 64GB M1 Max.

@radiofreejohn commented on GitHub (Jul 25, 2023): Are you sure you're not running out of memory? The assertion failure there looks like a check for available memory. I was able to build and run a model with `nous-hermes` and temperature 2 num_ctx 4096 on a 64GB M1 Max.
Author
Owner

@alivardar commented on GitHub (Jul 25, 2023):

My macbook air has 16gb ram, probably you are right. But seems application has no control about memory size control.

@alivardar commented on GitHub (Jul 25, 2023): My macbook air has 16gb ram, probably you are right. But seems application has no control about memory size control.
Author
Owner

@jmorganca commented on GitHub (Jul 25, 2023):

Thanks for creating this issue!

@jmorganca commented on GitHub (Jul 25, 2023): Thanks for creating this issue!
Author
Owner

@jmorganca commented on GitHub (Aug 23, 2023):

This should be fixed as of the last few versions, but feel free to re-open!

@jmorganca commented on GitHub (Aug 23, 2023): This should be fixed as of the last few versions, but feel free to re-open!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama-ollama#80