Eval bug: unknown pre-tokenizer type: 'deepseek-r1-qwen'

[wr131]

Name and Version

$./llama-cli --version version: 3680 (947538ac) built with cc (Debian 14.2.0-16) 14.2.0 for x86_64-linux-gnu

Operating systems

Linux

GGML backends

CPU

Hardware

Intel Celeron 1007U

Models

bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF

Problem description & steps to reproduce

I would to load deepseek-r1-distill-qwen-1.5B on my old PC, but it reported error that pre-tokenizer type is unknown.

llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-r1-qwen'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model
main: error: unable to load model

First Bad Commit

No response

Relevant log output

Log start
main: build = 3680 (947538ac)
main: built with cc (Debian 14.2.0-16) 14.2.0 for x86_64-linux-gnu
main: seed  = 1740215762
llama_model_loader: loaded meta data with 39 key-value pairs and 339 tensors from example.gguf (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.type str              = model
llama_model_loader: - kv   2:                               general.name str              = DeepSeek R1 Distill Qwen 1.5B
llama_model_loader: - kv   3:                           general.finetune str              = Abliterated
llama_model_loader: - kv   4:                           general.basename str              = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv   5:                         general.size_label str              = 1.5B
llama_model_loader: - kv   6:                   general.base_model.count u32              = 1
llama_model_loader: - kv   7:                  general.base_model.0.name str              = DeepSeek R1 Distill Qwen 1.5B
llama_model_loader: - kv   8:          general.base_model.0.organization str              = Deepseek Ai
llama_model_loader: - kv   9:              general.base_model.0.repo_url str              = https://huggingface.co/deepseek-ai/De...
llama_model_loader: - kv  10:                               general.tags arr[str,1]       = ["Distill"]
llama_model_loader: - kv  11:                          qwen2.block_count u32              = 28
llama_model_loader: - kv  12:                       qwen2.context_length u32              = 131072
llama_model_loader: - kv  13:                     qwen2.embedding_length u32              = 1536
llama_model_loader: - kv  14:                  qwen2.feed_forward_length u32              = 8960
llama_model_loader: - kv  15:                 qwen2.attention.head_count u32              = 12
llama_model_loader: - kv  16:              qwen2.attention.head_count_kv u32              = 2
llama_model_loader: - kv  17:                       qwen2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  18:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = deepseek-r1-qwen
llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 151646
llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  28:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  29:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  30:               general.quantization_version u32              = 2
llama_model_loader: - kv  31:                          general.file_type u32              = 14
llama_model_loader: - kv  32:                                general.url str              
= https://huggingface.co/bartowski/Deep...
llama_model_loader: - kv  33:              mradermacher.quantize_version str              = 2
llama_model_loader: - kv  34:                  mradermacher.quantized_by str              = mradermacher
llama_model_loader: - kv  35:                  mradermacher.quantized_at str              = 2025-01-24T22:47:13+01:00
llama_model_loader: - kv  36:                  mradermacher.quantized_on str              = rain
llama_model_loader: - kv  37:                         general.source.url str              = https://huggingface.co/bartowski/Deep...
llama_model_loader: - kv  38:                  mradermacher.convert_type str              = hf
llama_model_loader: - type  f32:  141 tensors
llama_model_loader: - type q4_K:  190 tensors
llama_model_loader: - type q5_K:    7 tensors
llama_model_loader: - type q6_K:    1 tensors
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-r1-qwen'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model
main: error: unable to load model