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 #3904] Error: llama runner process no longer running: -1 #48929

New Issue
Closed
opened 2026-04-28 10:10:40 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 10:10:40 -05:00
Owner
Copy Link

Originally created by @parthV2 on GitHub (Apr 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3904

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Was trying to run a finetuned version of llama2 having a gguf of 13.5gb.

Screenshot from 2024-04-25 11-30-55

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

v0.1.32

Originally created by @parthV2 on GitHub (Apr 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3904 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Was trying to run a finetuned version of llama2 having a gguf of 13.5gb. ![Screenshot from 2024-04-25 11-30-55](https://github.com/ollama/ollama/assets/163822058/99f79650-123b-4c84-8de2-ad697d97002a) ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version v0.1.32
GiteaMirror added the bug label 2026-04-28 10:10:41 -05:00
GiteaMirror commented 2026-04-28 10:10:50 -05:00
Author
Owner
Copy Link

@kannon92 commented on GitHub (Apr 25, 2024):

Can you get logs for the server? I’ve seen this error when I couldn’t load some linear algebra libraries.

<!-- gh-comment-id:2077109660 --> @kannon92 commented on GitHub (Apr 25, 2024): Can you get logs for the server? I’ve seen this error when I couldn’t load some linear algebra libraries.
GiteaMirror commented 2026-04-28 10:10:52 -05:00
Author
Owner
Copy Link

@MoonRide303 commented on GitHub (Apr 25, 2024):

Also happens when trying to load Phi-3 GGUF created with current llama.cpp versions:

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'phi3'
llama_load_model_from_file: exception loading model
time=2024-04-25T18:30:30.049+02:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: 3221226505 "
[GIN] 2024/04/25 - 18:30:30 | 500 |    536.2714ms |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:2077704160 --> @MoonRide303 commented on GitHub (Apr 25, 2024): Also happens when trying to load Phi-3 GGUF created with current llama.cpp versions: ``` llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'phi3' llama_load_model_from_file: exception loading model time=2024-04-25T18:30:30.049+02:00 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: 3221226505 " [GIN] 2024/04/25 - 18:30:30 | 500 | 536.2714ms | 127.0.0.1 | POST "/api/chat" ```
GiteaMirror commented 2026-04-28 10:10:53 -05:00
Author
Owner
Copy Link

@parthV2 commented on GitHub (Apr 26, 2024):

@kannon92 > logs for the server?

Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 345.721µs | 127.0.0.1 | HEAD "/"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 1.668953ms | 127.0.0.1 | POST "/api/show"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 327.883µs | 127.0.0.1 | POST "/api/show"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.272+05:30 level=INFO source=gpu.go:121 msg="Detecting GPU type"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.272+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.276+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0 /usr/local/cuda/lib64/libcudart.so.12.4.127 /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243]"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.417+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 100"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.562+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.127: cudart init failure: 100"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.720+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243: cudart init failure: 100"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.720+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.727+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67 /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00 /usr/lib32/libnvidia-ml.so.550.67]"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.849+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67: nvml vram init failure: 9"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.877+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00: nvml vram init failure: 9"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.878+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib32/libnvidia-ml.so.550.67: Unable to load /usr/lib32/libnvidia-ml.so.550.67 library to query for Nvidia GPUs: /usr/lib32/libnvidia-ml.so.550.67: wrong ELF class: ELFCLASS32"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.878+05:30 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.879+05:30 level=INFO source=gpu.go:121 msg="Detecting GPU type"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.879+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*"
Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.887+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0 /usr/local/cuda/lib64/libcudart.so.12.4.127 /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243]"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.004+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 100"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.120+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.127: cudart init failure: 100"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.252+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243: cudart init failure: 100"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.254+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.262+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67 /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00 /usr/lib32/libnvidia-ml.so.550.67]"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.308+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67: nvml vram init failure: 9"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00: nvml vram init failure: 9"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib32/libnvidia-ml.so.550.67: Unable to load /usr/lib32/libnvidia-ml.so.550.67 library to query for Nvidia GPUs: /usr/lib32/libnvidia-ml.so.550.67: wrong ELF class: ELFCLASS32"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=server.go:127 msg="offload to gpu" reallayers=0 layers=0 required="13791.0 MiB" used="193.0 MiB" available="0 B" kv="1024.0 MiB" fulloffload="164.0 MiB" partialoffload="193.0 MiB"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.322+05:30 level=INFO source=server.go:264 msg="starting llama server" cmd="/tmp/ollama695377432/runners/cpu_avx2/ollama_llama_server --model /usr/share/ollama/.ollama/models/blobs/sha256-86b805d4fd5c7881ae110aeedafc8062d6a504c6aa80145d41e00d0076b6cebe --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 0 --port 41521"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.322+05:30 level=INFO source=server.go:389 msg="waiting for llama runner to start responding"
Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"139646131890048","timestamp":1714024133}
Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"server_params_parse","level":"WARN","line":2380,"msg":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1,"tid":"139646131890048","timestamp":1714024133}
Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"build":1,"commit":"7593639","function":"main","level":"INFO","line":2819,"msg":"build info","tid":"139646131890048","timestamp":1714024133}
Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"main","level":"INFO","line":2822,"msg":"system info","n_threads":4,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | 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 = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | ","tid":"139646131890048","timestamp":1714024133,"total_threads":8}
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: loaded meta data with 26 key-value pairs and 323 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-86b805d4fd5c7881ae110aeedafc8062d6a504c6aa80145d41e00d0076b6cebe (version GGUF V3 (latest))
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 0: general.architecture str = llama
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 1: general.name str = Agri-llama
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 2: llama.block_count u32 = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 3: llama.context_length u32 = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 8: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 9: general.file_type u32 = 1
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 10: llama.vocab_size u32 = 32000
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 11: llama.rope.dimension_count u32 = 128
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 12: tokenizer.ggml.model str = llama
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["", "", "", "<0x00>", "<...
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'...
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 21: tokenizer.ggml.prefix_token_id u32 = 32007
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 22: tokenizer.ggml.suffix_token_id u32 = 32008
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 23: tokenizer.ggml.middle_token_id u32 = 32009
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 24: tokenizer.ggml.eot_token_id u32 = 32010
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 25: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'...
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - type f32: 97 tensors
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - type f16: 226 tensors
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_vocab: special tokens definition check successful ( 259/32000 ).
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: format = GGUF V3 (latest)
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: arch = llama
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: vocab type = SPM
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_vocab = 32000
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_merges = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_ctx_train = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_head = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_head_kv = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_layer = 32
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_rot = 128
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_head_k = 128
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_head_v = 128
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_gqa = 1
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_k_gqa = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_v_gqa = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_norm_eps = 0.0e+00
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_norm_rms_eps = 1.0e-05
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_clamp_kqv = 0.0e+00
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_logit_scale = 0.0e+00
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_ff = 11008
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_expert = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_expert_used = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: causal attn = 1
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: pooling type = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope type = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope scaling = linear
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: freq_base_train = 10000.0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: freq_scale_train = 1
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_yarn_orig_ctx = 4096
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope_finetuned = unknown
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_conv = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_inner = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_state = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_dt_rank = 0
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model type = 7B
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model ftype = F16
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model params = 6.74 B
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model size = 12.55 GiB (16.00 BPW)
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: general.name = Agri-llama
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: BOS token = 1 ''
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: EOS token = 2 ''
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: UNK token = 0 ''
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: PAD token = 0 ''
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: LF token = 13 '<0x0A>'
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_tensors: ggml ctx size = 0.12 MiB
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 323, got 291
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_load_model_from_file: exception loading model
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: terminate called after throwing an instance of 'std::runtime_error'
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: what(): done_getting_tensors: wrong number of tensors; expected 323, got 291
Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.736+05:30 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 "

<!-- gh-comment-id:2079034612 --> @parthV2 commented on GitHub (Apr 26, 2024): @kannon92 > logs for the server? Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 345.721µs | 127.0.0.1 | HEAD "/" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 1.668953ms | 127.0.0.1 | POST "/api/show" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: [GIN] 2024/04/25 - 11:18:52 | 200 | 327.883µs | 127.0.0.1 | POST "/api/show" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.272+05:30 level=INFO source=gpu.go:121 msg="Detecting GPU type" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.272+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.276+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0 /usr/local/cuda/lib64/libcudart.so.12.4.127 /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243]" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.417+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 100" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.562+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.127: cudart init failure: 100" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.720+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243: cudart init failure: 100" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.720+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.727+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67 /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00 /usr/lib32/libnvidia-ml.so.550.67]" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.849+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67: nvml vram init failure: 9" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.877+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00: nvml vram init failure: 9" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.878+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib32/libnvidia-ml.so.550.67: Unable to load /usr/lib32/libnvidia-ml.so.550.67 library to query for Nvidia GPUs: /usr/lib32/libnvidia-ml.so.550.67: wrong ELF class: ELFCLASS32" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.878+05:30 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.879+05:30 level=INFO source=gpu.go:121 msg="Detecting GPU type" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.879+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libcudart.so*" Apr 25 11:18:52 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:52.887+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0 /usr/local/cuda/lib64/libcudart.so.12.4.127 /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243]" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.004+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /tmp/ollama695377432/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 100" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.120+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/local/cuda/lib64/libcudart.so.12.4.127: cudart init failure: 100" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.252+05:30 level=INFO source=gpu.go:343 msg="Unable to load cudart CUDA management library /usr/lib/x86_64-linux-gnu/libcudart.so.10.1.243: cudart init failure: 100" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.254+05:30 level=INFO source=gpu.go:268 msg="Searching for GPU management library libnvidia-ml.so" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.262+05:30 level=INFO source=gpu.go:314 msg="Discovered GPU libraries: [/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67 /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00 /usr/lib32/libnvidia-ml.so.550.67]" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.308+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.550.67: nvml vram init failure: 9" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.418.226.00: nvml vram init failure: 9" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=gpu.go:326 msg="Unable to load NVML management library /usr/lib32/libnvidia-ml.so.550.67: Unable to load /usr/lib32/libnvidia-ml.so.550.67 library to query for Nvidia GPUs: /usr/lib32/libnvidia-ml.so.550.67: wrong ELF class: ELFCLASS32" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.321+05:30 level=INFO source=server.go:127 msg="offload to gpu" reallayers=0 layers=0 required="13791.0 MiB" used="193.0 MiB" available="0 B" kv="1024.0 MiB" fulloffload="164.0 MiB" partialoffload="193.0 MiB" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.322+05:30 level=INFO source=server.go:264 msg="starting llama server" cmd="/tmp/ollama695377432/runners/cpu_avx2/ollama_llama_server --model /usr/share/ollama/.ollama/models/blobs/sha256-86b805d4fd5c7881ae110aeedafc8062d6a504c6aa80145d41e00d0076b6cebe --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 0 --port 41521" Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.322+05:30 level=INFO source=server.go:389 msg="waiting for llama runner to start responding" Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"server_params_parse","level":"INFO","line":2603,"msg":"logging to file is disabled.","tid":"139646131890048","timestamp":1714024133} Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"server_params_parse","level":"WARN","line":2380,"msg":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1,"tid":"139646131890048","timestamp":1714024133} Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"build":1,"commit":"7593639","function":"main","level":"INFO","line":2819,"msg":"build info","tid":"139646131890048","timestamp":1714024133} Apr 25 11:18:53 vassar-Latitude-5490 ollama[12750]: {"function":"main","level":"INFO","line":2822,"msg":"system info","n_threads":4,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 0 | 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 = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | ","tid":"139646131890048","timestamp":1714024133,"total_threads":8} Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: loaded meta data with 26 key-value pairs and 323 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-86b805d4fd5c7881ae110aeedafc8062d6a504c6aa80145d41e00d0076b6cebe (version GGUF V3 (latest)) Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 0: general.architecture str = llama Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 1: general.name str = Agri-llama Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 2: llama.block_count u32 = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 3: llama.context_length u32 = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 5: llama.feed_forward_length u32 = 11008 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 8: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 9: general.file_type u32 = 1 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 10: llama.vocab_size u32 = 32000 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 11: llama.rope.dimension_count u32 = 128 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 12: tokenizer.ggml.model str = llama Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 20: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'... Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 21: tokenizer.ggml.prefix_token_id u32 = 32007 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 22: tokenizer.ggml.suffix_token_id u32 = 32008 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 23: tokenizer.ggml.middle_token_id u32 = 32009 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 24: tokenizer.ggml.eot_token_id u32 = 32010 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - kv 25: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'... Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - type f32: 97 tensors Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_loader: - type f16: 226 tensors Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_vocab: special tokens definition check successful ( 259/32000 ). Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: format = GGUF V3 (latest) Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: arch = llama Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: vocab type = SPM Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_vocab = 32000 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_merges = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_ctx_train = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_head = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_head_kv = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_layer = 32 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_rot = 128 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_head_k = 128 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_head_v = 128 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_gqa = 1 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_k_gqa = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_embd_v_gqa = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_norm_eps = 0.0e+00 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_norm_rms_eps = 1.0e-05 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_clamp_kqv = 0.0e+00 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: f_logit_scale = 0.0e+00 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_ff = 11008 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_expert = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_expert_used = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: causal attn = 1 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: pooling type = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope type = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope scaling = linear Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: freq_base_train = 10000.0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: freq_scale_train = 1 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: n_yarn_orig_ctx = 4096 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: rope_finetuned = unknown Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_conv = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_inner = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_d_state = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: ssm_dt_rank = 0 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model type = 7B Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model ftype = F16 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model params = 6.74 B Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: model size = 12.55 GiB (16.00 BPW) Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: general.name = Agri-llama Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: BOS token = 1 '<s>' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: EOS token = 2 '</s>' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: UNK token = 0 '<unk>' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: PAD token = 0 '<unk>' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_print_meta: LF token = 13 '<0x0A>' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llm_load_tensors: ggml ctx size = 0.12 MiB Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 323, got 291 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: llama_load_model_from_file: exception loading model Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: terminate called after throwing an instance of 'std::runtime_error' Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: what(): done_getting_tensors: wrong number of tensors; expected 323, got 291 Apr 25 11:18:53 vassar-Latitude-5490 ollama[6500]: time=2024-04-25T11:18:53.736+05:30 level=ERROR source=routes.go:120 msg="error loading llama server" error="llama runner process no longer running: -1 "
GiteaMirror commented 2026-04-28 10:10:54 -05:00
Author
Owner
Copy Link

@sanyuan0704 commented on GitHub (Apr 27, 2024):

I have the save issue with Phi3 model

<!-- gh-comment-id:2080386375 --> @sanyuan0704 commented on GitHub (Apr 27, 2024): I have the save issue with Phi3 model
GiteaMirror commented 2026-04-28 10:10:55 -05:00
Author
Owner
Copy Link

@lvoz2 commented on GitHub (Apr 30, 2024):

I have the same issue, after updating manually (This is on a Raspberry Pi 4B), but it is with Apple's new Open ELM. I used the conversion and quantization scripts from the pr by joshcarp, and have successfully built the GGUF file of OpenELM-270M. I want to test it, but that error is preventing me. Interesting, I can still run gemma:2b, although this was pulled with an older version of ollama

<!-- gh-comment-id:2085135398 --> @lvoz2 commented on GitHub (Apr 30, 2024): I have the same issue, after updating manually (This is on a Raspberry Pi 4B), but it is with Apple's new Open ELM. I used the conversion and quantization scripts from the [pr](https://github.com/ggerganov/llama.cpp/pull/6986) by joshcarp, and have successfully built the GGUF file of OpenELM-270M. I want to test it, but that error is preventing me. Interesting, I can still run gemma:2b, although this was pulled with an older version of ollama
GiteaMirror commented 2026-04-28 10:10:56 -05:00
Author
Owner
Copy Link

@parthV2 commented on GitHub (Apr 30, 2024):

** lvoz2I have 6 models in ollama...everyone is working well except this.

<!-- gh-comment-id:2085203939 --> @parthV2 commented on GitHub (Apr 30, 2024): > ### > ** [lvoz2](/lvoz2)I have 6 models in ollama...everyone is working well except this.
GiteaMirror commented 2026-04-28 10:10:57 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 1, 2024):

Initial support for phi3 was added in 0.1.32, and conversion should be working in 0.1.33. Please give the latest RC a try and let us know if you're still having problems.

https://github.com/ollama/ollama/releases

<!-- gh-comment-id:2089200635 --> @dhiltgen commented on GitHub (May 1, 2024): Initial support for phi3 was added in 0.1.32, and conversion should be working in 0.1.33. Please give the latest RC a try and let us know if you're still having problems. https://github.com/ollama/ollama/releases
GiteaMirror commented 2026-04-28 10:10:59 -05:00
Author
Owner
Copy Link

@Utopiah commented on GitHub (Jun 21, 2024):

Getting llama3 working but

fabien@fabien-CORSAIR-ONE-i160:~$ curl -fsSL https://ollama.com/install.sh | sh
>>> Downloading ollama...
######################################################################## 100.0%##O=#  #                                                                      
>>> Installing ollama to /usr/local/bin...
[sudo] password for fabien: 
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> NVIDIA GPU installed.
>>> The Ollama API is now available at 127.0.0.1:11434.
>>> Install complete. Run "ollama" from the command line.
fabien@fabien-CORSAIR-ONE-i160:~$ ollama run moondream
Error: llama runner process no longer running: -1 
fabien@fabien-CORSAIR-ONE-i160:~$ ollama run phi3
Error: llama runner process no longer running: -1 
fabien@fabien-CORSAIR-ONE-i160:~$ ollama -v
ollama version is 0.1.32
Warning: client version is 0.1.45

so does the curl install version not support updating?

<!-- gh-comment-id:2183184229 --> @Utopiah commented on GitHub (Jun 21, 2024): Getting llama3 working but ``` fabien@fabien-CORSAIR-ONE-i160:~$ curl -fsSL https://ollama.com/install.sh | sh >>> Downloading ollama... ######################################################################## 100.0%##O=# # >>> Installing ollama to /usr/local/bin... [sudo] password for fabien: >>> Adding ollama user to render group... >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> NVIDIA GPU installed. >>> The Ollama API is now available at 127.0.0.1:11434. >>> Install complete. Run "ollama" from the command line. fabien@fabien-CORSAIR-ONE-i160:~$ ollama run moondream Error: llama runner process no longer running: -1 fabien@fabien-CORSAIR-ONE-i160:~$ ollama run phi3 Error: llama runner process no longer running: -1 fabien@fabien-CORSAIR-ONE-i160:~$ ollama -v ollama version is 0.1.32 Warning: client version is 0.1.45 ``` so does the curl install version not support updating?
GiteaMirror commented 2026-04-28 10:11:00 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 21, 2024):

sudo systemctl restart ollama (or you can reboot)

<!-- gh-comment-id:2183250376 --> @dhiltgen commented on GitHub (Jun 21, 2024): `sudo systemctl restart ollama` (or you can reboot)
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#48929
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?