github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7618] llama runner process has terminated: signal: segmentation fault (core dumped) #4861

New Issue
Closed
opened 2026-04-12 15:51:39 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 15:51:39 -05:00
Owner
Copy Link

Originally created by @Dhruv-1212 on GitHub (Nov 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7618

What is the issue?

segmentation fault (core dumped) error for snowflake-arctic-embed:latest, other models are working fine

these are the system logs

Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.252Z level=INFO source=server.go:108 msg="system memory" total="29.4 GiB" free="26.9 GiB" free_swap="0 B"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.253Z level=INFO source=memory.go:326 msg="offload to cpu" layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[26.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="705.4 MiB" memory.required.partial="0 B" memory.required.kv="12.0 MiB" memory.required.allocations="[705.4 MiB]" memory.weights.total="589.2 MiB" memory.weights.repeating="529.6 MiB" memory.weights.nonrepeating="59.6 MiB" memory.graph.full="32.0 MiB" memory.graph.partial="32.0 MiB"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.255Z level=INFO source=server.go:399 msg="starting llama server" cmd="/tmp/ollama1595154785/runners/cpu_avx2/ollama_llama_server --model /var/snap/ollama/common/models/blobs/sha256-fb3b66c7bdf6dabbb2edbc22627f4cb2df021c9e9545b54feafd8a7c09fe8ec5 --ctx-size 2048 --batch-size 512 --embedding --log-disable --no-mmap --parallel 1 --port 35273"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=sched.go:449 msg="loaded runners" count=1
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[13066]: INFO [main] starting c++ runner | tid="134564798229440" timestamp=1731313564
Nov 11 08:26:04 dev--aiml-reco ollama.listener[13066]: INFO [main] build info | build=10 commit="3cd3d45b" tid="134564798229440" timestamp=1731313564
Nov 11 08:26:04 dev--aiml-reco ollama.listener[13066]: INFO [main] system info | n_threads=4 n_threads_batch=4 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | 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 | " tid="134564798229440" timestamp=1731313564 total_threads=8
Nov 11 08:26:04 dev--aiml-reco ollama.listener[13066]: INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="35273" tid="134564798229440" timestamp=1731313564
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: loaded meta data with 20 key-value pairs and 389 tensors from /var/snap/ollama/common/models/blobs/sha256-fb3b66c7bdf6dabbb2edbc22627f4cb2df021c9e9545b54feafd8a7c09fe8ec5 (version GGUF V3 (latest))
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 0: general.architecture str = bert
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 1: general.name str = snowflake-arctic-embed-l
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 2: bert.block_count u32 = 24
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 3: bert.context_length u32 = 512
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 4: bert.embedding_length u32 = 1024
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 5: bert.feed_forward_length u32 = 4096
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 6: bert.attention.head_count u32 = 16
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 7: bert.attention.layer_norm_epsilon f32 = 0.000000
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 8: general.file_type u32 = 1
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 9: bert.attention.causal bool = false
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 10: bert.pooling_type u32 = 2
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 11: tokenizer.ggml.token_type_count u32 = 2
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 12: tokenizer.ggml.model str = bert
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "...
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 100
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 16: tokenizer.ggml.seperator_token_id u32 = 102
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 18: tokenizer.ggml.cls_token_id u32 = 101
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - kv 19: tokenizer.ggml.mask_token_id u32 = 103
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - type f32: 243 tensors
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_model_loader: - type f16: 146 tensors
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_vocab: special tokens cache size = 5
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_vocab: token to piece cache size = 0.2032 MB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: format = GGUF V3 (latest)
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: arch = bert
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: vocab type = WPM
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_vocab = 30522
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_merges = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: vocab_only = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ctx_train = 512
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd = 1024
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_layer = 24
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_head = 16
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_head_kv = 16
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_rot = 64
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_swa = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_head_k = 64
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_head_v = 64
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_gqa = 1
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_k_gqa = 1024
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_v_gqa = 1024
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: f_norm_eps = 1.0e-12
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: f_norm_rms_eps = 0.0e+00
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: f_clamp_kqv = 0.0e+00
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: f_logit_scale = 0.0e+00
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ff = 4096
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_expert = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_expert_used = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: causal attn = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: pooling type = 2
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: rope type = 2
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: rope scaling = linear
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: freq_base_train = 10000.0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: freq_scale_train = 1
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ctx_orig_yarn = 512
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: rope_finetuned = unknown
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_conv = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_inner = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_state = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_dt_rank = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_dt_b_c_rms = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: model type = 335M
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: model ftype = F16
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: model params = 334.09 M
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: model size = 637.85 MiB (16.02 BPW)
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: general.name = snowflake-arctic-embed-l
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: UNK token = 100 '[UNK]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: SEP token = 102 '[SEP]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: PAD token = 0 '[PAD]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: CLS token = 101 '[CLS]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: MASK token = 103 '[MASK]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: LF token = 0 '[PAD]'
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_print_meta: max token length = 21
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_tensors: ggml ctx size = 0.16 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llm_load_tensors: CPU buffer size = 637.85 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.508Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_ctx = 2048
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_batch = 512
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_ubatch = 512
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: flash_attn = 0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: freq_base = 10000.0
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: freq_scale = 1
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_kv_cache_init: CPU KV buffer size = 192.00 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: CPU output buffer size = 0.00 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: CPU compute buffer size = 25.01 MiB
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: graph nodes = 849
Nov 11 08:26:04 dev--aiml-reco ollama.listener[1455]: llama_new_context_with_model: graph splits = 1
Nov 11 08:26:04 dev--aiml-reco kernel: ollama_llama_se[13066]: segfault at 7a629d9ff820 ip 00007a62cf570dc8 sp 00007fff67c94298 error 4 in libggml.so[7a62cf56e000+98000] likely on CPU 3 (core 3, socket 0)
Nov 11 08:26:04 dev--aiml-reco kernel: Code: 00 00 f3 0f 1e fa e9 77 ff ff ff 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 85 d2 7e 27 4c 8b 05 00 52 0b 00 31 c0 66 0f 1f 44 00 00 <0f> b7 0c 47 c4 c1 7a 10 04 88 c5 fa 11 04 86 48 83 c0 01 48 39 c2
Nov 11 08:26:05 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:05.032Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
Nov 11 08:26:05 dev--aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:05.282Z level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: signal: segmentation fault (core dumped)"
Nov 11 08:26:05 dev-_-aiml-reco ollama.listener[1455]: [GIN] 2024/11/11 - 08:26:05 | 500 | 1.038579932s | 127.0.0.1 | POST "/api/embeddings"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.0.0

Originally created by @Dhruv-1212 on GitHub (Nov 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7618 ### What is the issue? segmentation fault (core dumped) error for snowflake-arctic-embed:latest, other models are working fine these are the system logs Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.252Z level=INFO source=server.go:108 msg="system memory" total="29.4 GiB" free="26.9 GiB" free_swap="0 B" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.253Z level=INFO source=memory.go:326 msg="offload to cpu" layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[26.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="705.4 MiB" memory.required.partial="0 B" memory.required.kv="12.0 MiB" memory.required.allocations="[705.4 MiB]" memory.weights.total="589.2 MiB" memory.weights.repeating="529.6 MiB" memory.weights.nonrepeating="59.6 MiB" memory.graph.full="32.0 MiB" memory.graph.partial="32.0 MiB" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.255Z level=INFO source=server.go:399 msg="starting llama server" cmd="/tmp/ollama1595154785/runners/cpu_avx2/ollama_llama_server --model /var/snap/ollama/common/models/blobs/sha256-fb3b66c7bdf6dabbb2edbc22627f4cb2df021c9e9545b54feafd8a7c09fe8ec5 --ctx-size 2048 --batch-size 512 --embedding --log-disable --no-mmap --parallel 1 --port 35273" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=sched.go:449 msg="loaded runners" count=1 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.256Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[13066]: INFO [main] starting c++ runner | tid="134564798229440" timestamp=1731313564 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[13066]: INFO [main] build info | build=10 commit="3cd3d45b" tid="134564798229440" timestamp=1731313564 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[13066]: INFO [main] system info | n_threads=4 n_threads_batch=4 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | 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 | " tid="134564798229440" timestamp=1731313564 total_threads=8 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[13066]: INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="35273" tid="134564798229440" timestamp=1731313564 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: loaded meta data with 20 key-value pairs and 389 tensors from /var/snap/ollama/common/models/blobs/sha256-fb3b66c7bdf6dabbb2edbc22627f4cb2df021c9e9545b54feafd8a7c09fe8ec5 (version GGUF V3 (latest)) Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 0: general.architecture str = bert Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 1: general.name str = snowflake-arctic-embed-l Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 2: bert.block_count u32 = 24 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 3: bert.context_length u32 = 512 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 4: bert.embedding_length u32 = 1024 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 5: bert.feed_forward_length u32 = 4096 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 6: bert.attention.head_count u32 = 16 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 7: bert.attention.layer_norm_epsilon f32 = 0.000000 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 8: general.file_type u32 = 1 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 9: bert.attention.causal bool = false Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 10: bert.pooling_type u32 = 2 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 11: tokenizer.ggml.token_type_count u32 = 2 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 12: tokenizer.ggml.model str = bert Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,30522] = ["[PAD]", "[unused0]", "[unused1]", "... Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,30522] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 15: tokenizer.ggml.unknown_token_id u32 = 100 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 16: tokenizer.ggml.seperator_token_id u32 = 102 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 18: tokenizer.ggml.cls_token_id u32 = 101 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - kv 19: tokenizer.ggml.mask_token_id u32 = 103 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - type f32: 243 tensors Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_model_loader: - type f16: 146 tensors Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_vocab: special tokens cache size = 5 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_vocab: token to piece cache size = 0.2032 MB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: format = GGUF V3 (latest) Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: arch = bert Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: vocab type = WPM Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_vocab = 30522 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_merges = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: vocab_only = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ctx_train = 512 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd = 1024 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_layer = 24 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_head = 16 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_head_kv = 16 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_rot = 64 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_swa = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_head_k = 64 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_head_v = 64 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_gqa = 1 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_k_gqa = 1024 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_embd_v_gqa = 1024 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: f_norm_eps = 1.0e-12 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: f_norm_rms_eps = 0.0e+00 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: f_clamp_kqv = 0.0e+00 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: f_logit_scale = 0.0e+00 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ff = 4096 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_expert = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_expert_used = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: causal attn = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: pooling type = 2 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: rope type = 2 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: rope scaling = linear Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: freq_base_train = 10000.0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: freq_scale_train = 1 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: n_ctx_orig_yarn = 512 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: rope_finetuned = unknown Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_conv = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_inner = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_d_state = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_dt_rank = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: ssm_dt_b_c_rms = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: model type = 335M Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: model ftype = F16 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: model params = 334.09 M Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: model size = 637.85 MiB (16.02 BPW) Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: general.name = snowflake-arctic-embed-l Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: UNK token = 100 '[UNK]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: SEP token = 102 '[SEP]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: PAD token = 0 '[PAD]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: CLS token = 101 '[CLS]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: MASK token = 103 '[MASK]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: LF token = 0 '[PAD]' Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_print_meta: max token length = 21 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_tensors: ggml ctx size = 0.16 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llm_load_tensors: CPU buffer size = 637.85 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:04.508Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_ctx = 2048 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_batch = 512 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: n_ubatch = 512 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: flash_attn = 0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: freq_base = 10000.0 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: freq_scale = 1 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_kv_cache_init: CPU KV buffer size = 192.00 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: CPU output buffer size = 0.00 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: CPU compute buffer size = 25.01 MiB Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: graph nodes = 849 Nov 11 08:26:04 dev-_-aiml-reco ollama.listener[1455]: llama_new_context_with_model: graph splits = 1 Nov 11 08:26:04 dev-_-aiml-reco kernel: ollama_llama_se[13066]: segfault at 7a629d9ff820 ip 00007a62cf570dc8 sp 00007fff67c94298 error 4 in libggml.so[7a62cf56e000+98000] likely on CPU 3 (core 3, socket 0) Nov 11 08:26:04 dev-_-aiml-reco kernel: Code: 00 00 f3 0f 1e fa e9 77 ff ff ff 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 85 d2 7e 27 4c 8b 05 00 52 0b 00 31 c0 66 0f 1f 44 00 00 <0f> b7 0c 47 c4 c1 7a 10 04 88 c5 fa 11 04 86 48 83 c0 01 48 39 c2 Nov 11 08:26:05 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:05.032Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" Nov 11 08:26:05 dev-_-aiml-reco ollama.listener[1455]: time=2024-11-11T08:26:05.282Z level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: signal: segmentation fault (core dumped)" Nov 11 08:26:05 dev-_-aiml-reco ollama.listener[1455]: [GIN] 2024/11/11 - 08:26:05 | 500 | 1.038579932s | 127.0.0.1 | POST "/api/embeddings" ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.0.0
GiteaMirror added the bug label 2026-04-12 15:51:39 -05:00
GiteaMirror commented 2026-04-12 15:51:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 11, 2024):

Does it work if you use an official release?

<!-- gh-comment-id:2468058148 --> @rick-github commented on GitHub (Nov 11, 2024): Does it work if you use an official release?
GiteaMirror commented 2026-04-12 15:51:43 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 11, 2024):

I would also recommend trying the current 0.4.1 release, which has the newer runner architecture.

<!-- gh-comment-id:2468828719 --> @jessegross commented on GitHub (Nov 11, 2024): I would also recommend trying the current 0.4.1 release, which has the newer runner architecture.
GiteaMirror commented 2026-04-12 15:51:44 -05:00
Author
Owner
Copy Link

@Dhruv-1212 commented on GitHub (Nov 12, 2024):

I installed it with the linux installation command provided on git, so it should be the latest installation, but it is showing version to be 0.0.0.
later I installed 0.3.5 and it worked.

<!-- gh-comment-id:2470040812 --> @Dhruv-1212 commented on GitHub (Nov 12, 2024): I installed it with the linux installation command provided on git, so it should be the latest installation, but it is showing version to be 0.0.0. later I installed 0.3.5 and it worked.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4861
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?