Alpaca crashes after prompting LLM

[kimjongbing]

Describe the bug
Alpaca crashes after it starts to respond to a prompt.

Expected behavior
Ability to respond to prompt without crashing.

Debugging information

INFO	[main.py | main] Alpaca version: 2.0.3
INFO	[connection_handler.py | start] Starting Alpaca's Ollama instance...
INFO	[connection_handler.py | start] Started Alpaca's Ollama instance
Error: listen tcp 127.0.0.1:11435: bind: address already in use
INFO	[connection_handler.py | start] client version is 0.3.9
INFO	[connection_handler.py | request] GET : http://127.0.0.1:11435/api/tags
ERROR	[model_widget.py | update_local_list] ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))
ERROR	[window.py | connection_error] Connection error
INFO	[connection_handler.py | reset] Resetting Alpaca's Ollama instance
INFO	[connection_handler.py | stop] Stopping Alpaca's Ollama instance
INFO	[connection_handler.py | stop] Stopped Alpaca's Ollama instance
INFO	[connection_handler.py | start] Starting Alpaca's Ollama instance...
INFO	[connection_handler.py | start] Started Alpaca's Ollama instance
2024/09/20 14:23:43 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11435 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/nadeko/.var/app/com.jeffser.Alpaca/data/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-09-20T14:23:43.192+10:00 level=INFO source=images.go:753 msg="total blobs: 5"
time=2024-09-20T14:23:43.192+10:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-09-20T14:23:43.192+10:00 level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11435 (version 0.3.9)"
time=2024-09-20T14:23:43.193+10:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/home/nadeko/.var/app/com.jeffser.Alpaca/cache/tmp/ollama/ollama339259155/runners
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu file=build/linux/x86_64/cpu/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu file=build/linux/x86_64/cpu/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu file=build/linux/x86_64/cpu/bin/ollama_llama_server.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx file=build/linux/x86_64/cpu_avx/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx file=build/linux/x86_64/cpu_avx/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx file=build/linux/x86_64/cpu_avx/bin/ollama_llama_server.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx2 file=build/linux/x86_64/cpu_avx2/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx2 file=build/linux/x86_64/cpu_avx2/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cpu_avx2 file=build/linux/x86_64/cpu_avx2/bin/ollama_llama_server.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v11 file=build/linux/x86_64/cuda_v11/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v11 file=build/linux/x86_64/cuda_v11/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v11 file=build/linux/x86_64/cuda_v11/bin/ollama_llama_server.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v12 file=build/linux/x86_64/cuda_v12/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v12 file=build/linux/x86_64/cuda_v12/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=cuda_v12 file=build/linux/x86_64/cuda_v12/bin/ollama_llama_server.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=rocm_v60102 file=build/linux/x86_64/rocm_v60102/bin/libggml.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=rocm_v60102 file=build/linux/x86_64/rocm_v60102/bin/libllama.so.gz
time=2024-09-20T14:23:43.193+10:00 level=DEBUG source=payload.go:182 msg=extracting variant=rocm_v60102 file=build/linux/x86_64/rocm_v60102/bin/ollama_llama_server.gz
INFO	[connection_handler.py | start] client version is 0.3.9
INFO	[window.py | show_toast] There was an error with the local Ollama instance, so it has been reset

Additional information
I am using llama 3.1 and the flatpak for this application.

Last few lines when it crashes:

(alpaca:2): Gtk-WARNING **: 14:22:21.879: Trying to snapshot GtkBox 0x61626c1696c0 without a current allocation

(alpaca:2): Gtk-WARNING **: 14:22:29.165: Trying to snapshot AdwOverlaySplitView 0x616269d1d7f0 without a current allocation
DEBUG [print_timings] prompt eval time     =     555.62 ms /   327 tokens (    1.70 ms per token,   588.53 tokens per second) | n_prompt_tokens_processed=327 n_tokens_second=588.530671086946 slot_id=0 t_prompt_processing=555.621 t_token=1.6991467889908256 task_id=4 tid="137254376472576" timestamp=1726806150
DEBUG [print_timings] generation eval time =   12448.28 ms /   408 runs   (   30.51 ms per token,    32.78 tokens per second) | n_decoded=408 n_tokens_second=32.77559920904768 slot_id=0 t_token=30.510502450980393 t_token_generation=12448.285 task_id=4 tid="137254376472576" timestamp=1726806150
DEBUG [print_timings]           total time =   13003.91 ms | slot_id=0 t_prompt_processing=555.621 t_token_generation=12448.285 t_total=13003.905999999999 task_id=4 tid="137254376472576" timestamp=1726806150
DEBUG [update_slots] slot released | n_cache_tokens=735 n_ctx=8192 n_past=734 n_system_tokens=0 slot_id=0 task_id=4 tid="137254376472576" timestamp=1726806150 truncated=false
DEBUG [log_server_request] request | method="POST" params={} path="/completion" remote_addr="127.0.0.1" remote_port=36310 status=200 tid="137253093376000" timestamp=1726806150
[GIN] 2024/09/20 - 14:22:30 | 200 | 16.123497729s |       127.0.0.1 | POST     "/api/chat"
time=2024-09-20T14:22:30.457+10:00 level=DEBUG source=sched.go:467 msg="context for request finished"
time=2024-09-20T14:22:30.457+10:00 level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/home/nadeko/.var/app/com.jeffser.Alpaca/data/.ollama/models/blobs/sha256-8eeb52dfb3bb9aefdf9d1ef24b3bdbcfbe82238798c4b918278320b6fcef18fe duration=5m0s
time=2024-09-20T14:22:30.457+10:00 level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/home/nadeko/.var/app/com.jeffser.Alpaca/data/.ollama/models/blobs/sha256-8eeb52dfb3bb9aefdf9d1ef24b3bdbcfbe82238798c4b918278320b6fcef18fe refCount=0

(alpaca:2): Gtk-CRITICAL **: 14:22:30.502: gtk_text_attributes_ref: assertion 'values != NULL' failed

(alpaca:2): Gtk-CRITICAL **: 14:22:30.502: gtk_text_attributes_ref: assertion 'values != NULL' failed

(alpaca:2): Pango-CRITICAL **: 14:22:30.502: pango_layout_new: assertion 'context != NULL' failed

[Jeffser]

Hi thanks for the report, this bug has been fixed in the latest release of Alpaca, please reopen the issue if you have any other problem, thanks