error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

[HouseYeung]

What is the issue?

llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

i was running qwen1.5-8B-chat

the old version of ollama can run this model properly.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.37

[satindergrewal]

Yes, I am also getting the same error on MacOS, Macbook Pro M3 Max, 128GB.

(base) ➜  ollama run Dolphin-2.9.1-Qwen-110b
Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
(base) ➜  ollama --version
ollama version is 0.1.37
(base) ➜ 

[Anorid]

Mine is also having this error and I'm running, qwen1.5-14b model

[Anorid]

This was my mistake

root@autodl-container-c438119a3c-80821c25:~/autodl-tmp# ollama serve
2024/05/20 11:28:20 routes.go:1008: INFO server config env="map[OLLAMA_DEBUG:false OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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:*] OLLAMA_RUNNERS_DIR: OLLAMA_TMPDIR:]"
time=2024-05-20T11:28:20.921+08:00 level=INFO source=images.go:704 msg="total blobs: 0"
time=2024-05-20T11:28:20.921+08:00 level=INFO source=images.go:711 msg="total unused blobs removed: 0"
time=2024-05-20T11:28:20.922+08:00 level=INFO source=routes.go:1054 msg="Listening on [::]:6006 (version 0.1.38)"
time=2024-05-20T11:28:20.922+08:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama2749468660/runners
time=2024-05-20T11:28:24.936+08:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2 cuda_v11 rocm_v60002]"
time=2024-05-20T11:28:25.117+08:00 level=INFO source=types.go:71 msg="inference compute" id=GPU-0f3aa8d5-c5ed-3fa3-1cb4-4aef2d3d8317 library=cuda compute=8.6 driver=12.2 name="NVIDIA A40" total="47.5 GiB" available="47.3 GiB"
[GIN] 2024/05/20 - 11:32:05 | 200 | 86.076µs | 127.0.0.1 | HEAD "/"
[GIN] 2024/05/20 - 11:32:29 | 201 | 12.804363258s | 127.0.0.1 | POST "/api/blobs/sha256:1c751709783923dab2b876d5c5c2ca36d4e205cfef7d88988df45752cb91f245"
[GIN] 2024/05/20 - 11:32:43 | 200 | 14.155378431s | 127.0.0.1 | POST "/api/create"
[GIN] 2024/05/20 - 11:33:04 | 200 | 35.782µs | 127.0.0.1 | HEAD "/"
[GIN] 2024/05/20 - 11:33:04 | 200 | 1.190285ms | 127.0.0.1 | POST "/api/show"
[GIN] 2024/05/20 - 11:33:04 | 200 | 737.579µs | 127.0.0.1 | POST "/api/show"
time=2024-05-20T11:33:06.243+08:00 level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=41 memory.available="47.3 GiB" memory.required.full="9.7 GiB" memory.required.partial="9.7 GiB" memory.required.kv="1.6 GiB" memory.weights.total="7.2 GiB" memory.weights.repeating="6.6 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
time=2024-05-20T11:33:06.244+08:00 level=INFO source=memory.go:133 msg="offload to gpu" layers.requested=-1 layers.real=41 memory.available="47.3 GiB" memory.required.full="9.7 GiB" memory.required.partial="9.7 GiB" memory.required.kv="1.6 GiB" memory.weights.total="7.2 GiB" memory.weights.repeating="6.6 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
time=2024-05-20T11:33:06.244+08:00 level=INFO source=server.go:320 msg="starting llama server" cmd="/tmp/ollama2749468660/runners/cuda_v11/ollama_llama_server --model /root/autodl-tmp/model/blobs/sha256-1c751709783923dab2b876d5c5c2ca36d4e205cfef7d88988df45752cb91f245 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 41 --parallel 1 --port 39195"
time=2024-05-20T11:33:06.245+08:00 level=INFO source=sched.go:338 msg="loaded runners" count=1
time=2024-05-20T11:33:06.245+08:00 level=INFO source=server.go:504 msg="waiting for llama runner to start responding"
time=2024-05-20T11:33:06.245+08:00 level=INFO source=server.go:540 msg="waiting for server to become available" status="llm server error"
INFO [main] build info | build=1 commit="952d03d" tid="140637096448000" timestamp=1716175986
INFO [main] system info | n_threads=64 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="140637096448000" timestamp=1716175986 total_threads=128
INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="127" port="39195" tid="140637096448000" timestamp=1716175986
llama_model_loader: loaded meta data with 21 key-value pairs and 483 tensors from /root/autodl-tmp/model/blobs/sha256-1c751709783923dab2b876d5c5c2ca36d4e205cfef7d88988df45752cb91f245 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = qwen2
llama_model_loader: - kv 1: general.name str = merge5-1
llama_model_loader: - kv 2: qwen2.block_count u32 = 40
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 5120
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 13696
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 40
llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 40
llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 10: general.file_type u32 = 2
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 151643
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 19: tokenizer.chat_template str = {% for message in messages %}{% if lo...
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 201 tensors
llama_model_loader: - type q4_0: 281 tensors
llama_model_loader: - type q6_K: 1 tensors
time=2024-05-20T11:33:06.497+08:00 level=INFO source=server.go:540 msg="waiting for server to become available" status="llm server loading model"
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
llama_load_model_from_file: exception loading model
terminate called after throwing an instance of 'std::runtime_error'
what(): error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
time=2024-05-20T11:33:06.872+08:00 level=INFO source=server.go:540 msg="waiting for server to become available" status="llm server error"
time=2024-05-20T11:33:07.122+08:00 level=ERROR source=sched.go:344 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped) "
[GIN] 2024/05/20 - 11:33:07 | 500 | 2.21829574s | 127.0.0.1 | POST "/api/chat"
time=2024-05-20T11:33:12.234+08:00 level=WARN source=sched.go:512 msg="gpu VRAM usage didn't recover within timeout" seconds=5.112074522
time=2024-05-20T11:33:12.485+08:00 level=WARN source=sched.go:512 msg="gpu VRAM usage didn't recover within timeout" seconds=5.362608222
time=2024-05-20T11:33:12.734+08:00 level=WARN source=sched.go:512 msg="gpu VRAM usage didn't recover within timeout" seconds=5.612062447

[GitTurboy]

I got the same error on windows system:
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from D:\lamaModels\blobs\sha256-6b22d907af67d494c1194b1bd688423945b4d3009bded2e5ecbc88d426b0c5a3 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = qwen2
llama_model_loader: - kv 1: general.name str = Qwen1___5-1___8B-Chat
llama_model_loader: - kv 2: qwen2.block_count u32 = 24
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 2048
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 5504
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 16
llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 9: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,151936] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 19: tokenizer.chat_template str = {% for message in messages %}{% if lo...
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - type f32: 121 tensors
llama_model_loader: - type f16: 170 tensors
time=2024-05-20T16:44:58.427+08:00 level=INFO source=server.go:540 msg="waiting for server to become available" status="llm server loading model"
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
llama_load_model_from_file: exception loading model
time=2024-05-20T16:44:58.698+08:00 level=ERROR source=sched.go:344 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 "

[songofhawk]

I got the same one: Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'