gpt-oss 20b not running #7764

New Issue

GiteaMirror · 2025-11-12T14:18:21-06:00

GiteaMirror commented

2025-11-12 14:18:21 -06:00

Originally created by @BeshoyEhab on GitHub (Aug 6, 2025).

What is the issue?

The issue is I have been pulled gpt-oss:latest and when I try to run it with ollama run gpt-oss:latest it gives me that error Error: template: :3: function "currentDate" not defined and I don't know how to solve it

Relevant log output

Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.193+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="8.3 GiB" free_swap="14.7 GiB"
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.193+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[8.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="0 B" memory.required.kv="576.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB" memory.weights.nonrepeating="486.9 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB"
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: loaded meta data with 32 key-value pairs and 399 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d (version GGUF V3 (latest))
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   0:                       general.architecture str              = qwen3
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   1:                               general.type str              = model
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   2:                               general.name str              = DeepSeek R1 0528 Qwen3 8B
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-0528-Qwen3
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   4:                         general.size_label str              = 8B
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   5:                            general.license str              = mit
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   6:                          qwen3.block_count u32              = 36
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   7:                       qwen3.context_length u32              = 131072
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   8:                     qwen3.embedding_length u32              = 4096
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   9:                  qwen3.feed_forward_length u32              = 12288
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  10:                 qwen3.attention.head_count u32              = 32
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  11:              qwen3.attention.head_count_kv u32              = 8
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  12:                       qwen3.rope.freq_base f32              = 1000000.000000
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  13:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  14:                 qwen3.attention.key_length u32              = 128
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  15:               qwen3.attention.value_length u32              = 128
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  16:                    qwen3.rope.scaling.type str              = yarn
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  17:                  qwen3.rope.scaling.factor f32              = 4.000000
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  18: qwen3.rope.scaling.original_context_length u32              = 32768
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = qwen2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 151643
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151645
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151645
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  28:               tokenizer.ggml.add_eos_token bool             = false
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  29:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  30:               general.quantization_version u32              = 2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  31:                          general.file_type u32              = 15
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type  f32:  145 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type  f16:   36 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q4_K:  199 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q6_K:   19 tensors
Aug 06 07:22:21 arch ollama[646637]: print_info: file format = GGUF V3 (latest)
Aug 06 07:22:21 arch ollama[646637]: print_info: file type   = Q4_K - Medium
Aug 06 07:22:21 arch ollama[646637]: print_info: file size   = 4.86 GiB (5.10 BPW)
Aug 06 07:22:21 arch ollama[646637]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
Aug 06 07:22:21 arch ollama[646637]: load: special tokens cache size = 28
Aug 06 07:22:21 arch ollama[646637]: load: token to piece cache size = 0.9311 MB
Aug 06 07:22:21 arch ollama[646637]: print_info: arch             = qwen3
Aug 06 07:22:21 arch ollama[646637]: print_info: vocab_only       = 1
Aug 06 07:22:21 arch ollama[646637]: print_info: model type       = ?B
Aug 06 07:22:21 arch ollama[646637]: print_info: model params     = 8.19 B
Aug 06 07:22:21 arch ollama[646637]: print_info: general.name     = DeepSeek R1 0528 Qwen3 8B
Aug 06 07:22:21 arch ollama[646637]: print_info: vocab type       = BPE
Aug 06 07:22:21 arch ollama[646637]: print_info: n_vocab          = 151936
Aug 06 07:22:21 arch ollama[646637]: print_info: n_merges         = 151387
Aug 06 07:22:21 arch ollama[646637]: print_info: BOS token        = 151643 '<｜begin▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOS token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOT token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: PAD token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: LF token         = 198 'Ċ'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151662 '<|fim_pad|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151663 '<|repo_name|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151664 '<|file_sep|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: max token length = 256
Aug 06 07:22:21 arch ollama[646637]: llama_model_load: vocab only - skipping tensors
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d --ctx-size 4096 --batch-size 512 --threads 8 --no-mmap --parallel 1 --port 34909"
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=sched.go:481 msg="loaded runners" count=1
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.503+03:00 level=INFO source=runner.go:815 msg="starting go runner"
Aug 06 07:22:21 arch ollama[646637]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.520+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.521+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:34909"
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: loaded meta data with 32 key-value pairs and 399 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d (version GGUF V3 (latest))
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   0:                       general.architecture str              = qwen3
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   1:                               general.type str              = model
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   2:                               general.name str              = DeepSeek R1 0528 Qwen3 8B
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-0528-Qwen3
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   4:                         general.size_label str              = 8B
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   5:                            general.license str              = mit
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   6:                          qwen3.block_count u32              = 36
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   7:                       qwen3.context_length u32              = 131072
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   8:                     qwen3.embedding_length u32              = 4096
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv   9:                  qwen3.feed_forward_length u32              = 12288
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  10:                 qwen3.attention.head_count u32              = 32
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  11:              qwen3.attention.head_count_kv u32              = 8
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  12:                       qwen3.rope.freq_base f32              = 1000000.000000
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  13:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  14:                 qwen3.attention.key_length u32              = 128
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  15:               qwen3.attention.value_length u32              = 128
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  16:                    qwen3.rope.scaling.type str              = yarn
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  17:                  qwen3.rope.scaling.factor f32              = 4.000000
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  18: qwen3.rope.scaling.original_context_length u32              = 32768
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = qwen2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 151643
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151645
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151645
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  28:               tokenizer.ggml.add_eos_token bool             = false
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  29:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  30:               general.quantization_version u32              = 2
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv  31:                          general.file_type u32              = 15
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type  f32:  145 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type  f16:   36 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q4_K:  199 tensors
Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q6_K:   19 tensors
Aug 06 07:22:21 arch ollama[646637]: print_info: file format = GGUF V3 (latest)
Aug 06 07:22:21 arch ollama[646637]: print_info: file type   = Q4_K - Medium
Aug 06 07:22:21 arch ollama[646637]: print_info: file size   = 4.86 GiB (5.10 BPW)
Aug 06 07:22:21 arch ollama[646637]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
Aug 06 07:22:21 arch ollama[646637]: load: special tokens cache size = 28
Aug 06 07:22:21 arch ollama[646637]: load: token to piece cache size = 0.9311 MB
Aug 06 07:22:21 arch ollama[646637]: print_info: arch             = qwen3
Aug 06 07:22:21 arch ollama[646637]: print_info: vocab_only       = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: n_ctx_train      = 131072
Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd           = 4096
Aug 06 07:22:21 arch ollama[646637]: print_info: n_layer          = 36
Aug 06 07:22:21 arch ollama[646637]: print_info: n_head           = 32
Aug 06 07:22:21 arch ollama[646637]: print_info: n_head_kv        = 8
Aug 06 07:22:21 arch ollama[646637]: print_info: n_rot            = 128
Aug 06 07:22:21 arch ollama[646637]: print_info: n_swa            = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: n_swa_pattern    = 1
Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_head_k    = 128
Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_head_v    = 128
Aug 06 07:22:21 arch ollama[646637]: print_info: n_gqa            = 4
Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_k_gqa     = 1024
Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_v_gqa     = 1024
Aug 06 07:22:21 arch ollama[646637]: print_info: f_norm_eps       = 0.0e+00
Aug 06 07:22:21 arch ollama[646637]: print_info: f_norm_rms_eps   = 1.0e-06
Aug 06 07:22:21 arch ollama[646637]: print_info: f_clamp_kqv      = 0.0e+00
Aug 06 07:22:21 arch ollama[646637]: print_info: f_max_alibi_bias = 0.0e+00
Aug 06 07:22:21 arch ollama[646637]: print_info: f_logit_scale    = 0.0e+00
Aug 06 07:22:21 arch ollama[646637]: print_info: f_attn_scale     = 0.0e+00
Aug 06 07:22:21 arch ollama[646637]: print_info: n_ff             = 12288
Aug 06 07:22:21 arch ollama[646637]: print_info: n_expert         = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: n_expert_used    = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: causal attn      = 1
Aug 06 07:22:21 arch ollama[646637]: print_info: pooling type     = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: rope type        = 2
Aug 06 07:22:21 arch ollama[646637]: print_info: rope scaling     = yarn
Aug 06 07:22:21 arch ollama[646637]: print_info: freq_base_train  = 1000000.0
Aug 06 07:22:21 arch ollama[646637]: print_info: freq_scale_train = 0.25
Aug 06 07:22:21 arch ollama[646637]: print_info: n_ctx_orig_yarn  = 32768
Aug 06 07:22:21 arch ollama[646637]: print_info: rope_finetuned   = unknown
Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_conv       = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_inner      = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_state      = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_dt_rank      = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_dt_b_c_rms   = 0
Aug 06 07:22:21 arch ollama[646637]: print_info: model type       = 8B
Aug 06 07:22:21 arch ollama[646637]: print_info: model params     = 8.19 B
Aug 06 07:22:21 arch ollama[646637]: print_info: general.name     = DeepSeek R1 0528 Qwen3 8B
Aug 06 07:22:21 arch ollama[646637]: print_info: vocab type       = BPE
Aug 06 07:22:21 arch ollama[646637]: print_info: n_vocab          = 151936
Aug 06 07:22:21 arch ollama[646637]: print_info: n_merges         = 151387
Aug 06 07:22:21 arch ollama[646637]: print_info: BOS token        = 151643 '<｜begin▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOS token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOT token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: PAD token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: LF token         = 198 'Ċ'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151645 '<｜end▁of▁sentence｜>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151662 '<|fim_pad|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151663 '<|repo_name|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token        = 151664 '<|file_sep|>'
Aug 06 07:22:21 arch ollama[646637]: print_info: max token length = 256
Aug 06 07:22:21 arch ollama[646637]: load_tensors: loading model tensors, this can take a while... (mmap = false)
Aug 06 07:22:21 arch ollama[646637]: load_tensors:          CPU model buffer size =  4977.62 MiB
Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.737+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Aug 06 07:22:27 arch ollama[646637]: llama_context: constructing llama_context
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_seq_max     = 1
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx         = 4096
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx_per_seq = 4096
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_batch       = 512
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ubatch      = 512
Aug 06 07:22:27 arch ollama[646637]: llama_context: causal_attn   = 1
Aug 06 07:22:27 arch ollama[646637]: llama_context: flash_attn    = 0
Aug 06 07:22:27 arch ollama[646637]: llama_context: freq_base     = 1000000.0
Aug 06 07:22:27 arch ollama[646637]: llama_context: freq_scale    = 0.25
Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
Aug 06 07:22:27 arch ollama[646637]: llama_context:        CPU  output buffer size =     0.60 MiB
Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32
Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified:        CPU KV buffer size =   576.00 MiB
Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified: KV self size  =  576.00 MiB, K (f16):  288.00 MiB, V (f16):  288.00 MiB
Aug 06 07:22:27 arch ollama[646637]: llama_context:        CPU compute buffer size =   304.75 MiB
Aug 06 07:22:27 arch ollama[646637]: llama_context: graph nodes  = 1374
Aug 06 07:22:27 arch ollama[646637]: llama_context: graph splits = 1
Aug 06 07:22:27 arch ollama[646637]: time=2025-08-06T07:22:27.757+03:00 level=INFO source=server.go:637 msg="llama runner started in 6.27 seconds"
Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.805+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="7.3 GiB" free_swap="14.9 GiB"
Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.805+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[7.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.8 GiB" memory.required.partial="0 B" memory.required.kv="192.0 MiB" memory.required.allocations="[2.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB"
Aug 06 07:40:46 arch ollama[646637]: gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' of type 4 (DEPRECATED) has 2880 elements per row, not a multiple of block size (0)
Aug 06 07:40:46 arch ollama[646637]: gguf_init_from_file_impl: failed to read tensor info
Aug 06 07:40:46 arch ollama[646637]: llama_model_load: error loading model: llama_model_loader: failed to load model from /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583
Aug 06 07:40:46 arch ollama[646637]: llama_model_load_from_file_impl: failed to load model
Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.883+03:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583"
Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.381+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="7.2 GiB" free_swap="14.9 GiB"
Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.381+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[7.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.8 GiB" memory.required.partial="0 B" memory.required.kv="192.0 MiB" memory.required.allocations="[2.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB"
Aug 06 07:41:16 arch ollama[646637]: gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' of type 4 (DEPRECATED) has 2880 elements per row, not a multiple of block size (0)
Aug 06 07:41:16 arch ollama[646637]: gguf_init_from_file_impl: failed to read tensor info
Aug 06 07:41:16 arch ollama[646637]: llama_model_load: error loading model: llama_model_loader: failed to load model from /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583
Aug 06 07:41:16 arch ollama[646637]: llama_model_load_from_file_impl: failed to load model
Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.442+03:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583"

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.11.0

Originally created by @BeshoyEhab on GitHub (Aug 6, 2025). ### What is the issue? The issue is I have been pulled gpt-oss:latest and when I try to run it with `ollama run gpt-oss:latest` it gives me that error `Error: template: :3: function "currentDate" not defined` and I don't know how to solve it ### Relevant log output ```shell Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.193+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="8.3 GiB" free_swap="14.7 GiB" Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.193+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=37 layers.offload=0 layers.split="" memory.available="[8.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="0 B" memory.required.kv="576.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB" memory.weights.nonrepeating="486.9 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB" Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: loaded meta data with 32 key-value pairs and 399 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d (version GGUF V3 (latest)) Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 0: general.architecture str = qwen3 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 1: general.type str = model Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 2: general.name str = DeepSeek R1 0528 Qwen3 8B Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-0528-Qwen3 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 4: general.size_label str = 8B Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 5: general.license str = mit Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 6: qwen3.block_count u32 = 36 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 7: qwen3.context_length u32 = 131072 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 8: qwen3.embedding_length u32 = 4096 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 12288 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 16: qwen3.rope.scaling.type str = yarn Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 17: qwen3.rope.scaling.factor f32 = 4.000000 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 18: qwen3.rope.scaling.original_context_length u32 = 32768 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 19: tokenizer.ggml.model str = gpt2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 20: tokenizer.ggml.pre str = qwen2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 23: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 151645 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 151645 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 28: tokenizer.ggml.add_eos_token bool = false Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 29: tokenizer.chat_template str = {% if not add_generation_prompt is de... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 30: general.quantization_version u32 = 2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 31: general.file_type u32 = 15 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type f32: 145 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type f16: 36 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q4_K: 199 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q6_K: 19 tensors Aug 06 07:22:21 arch ollama[646637]: print_info: file format = GGUF V3 (latest) Aug 06 07:22:21 arch ollama[646637]: print_info: file type = Q4_K - Medium Aug 06 07:22:21 arch ollama[646637]: print_info: file size = 4.86 GiB (5.10 BPW) Aug 06 07:22:21 arch ollama[646637]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect Aug 06 07:22:21 arch ollama[646637]: load: special tokens cache size = 28 Aug 06 07:22:21 arch ollama[646637]: load: token to piece cache size = 0.9311 MB Aug 06 07:22:21 arch ollama[646637]: print_info: arch = qwen3 Aug 06 07:22:21 arch ollama[646637]: print_info: vocab_only = 1 Aug 06 07:22:21 arch ollama[646637]: print_info: model type = ?B Aug 06 07:22:21 arch ollama[646637]: print_info: model params = 8.19 B Aug 06 07:22:21 arch ollama[646637]: print_info: general.name = DeepSeek R1 0528 Qwen3 8B Aug 06 07:22:21 arch ollama[646637]: print_info: vocab type = BPE Aug 06 07:22:21 arch ollama[646637]: print_info: n_vocab = 151936 Aug 06 07:22:21 arch ollama[646637]: print_info: n_merges = 151387 Aug 06 07:22:21 arch ollama[646637]: print_info: BOS token = 151643 '<｜begin▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOS token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOT token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: PAD token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: LF token = 198 'Ċ' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM MID token = 151660 '<|fim_middle|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM REP token = 151663 '<|repo_name|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SEP token = 151664 '<|file_sep|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151662 '<|fim_pad|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151663 '<|repo_name|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151664 '<|file_sep|>' Aug 06 07:22:21 arch ollama[646637]: print_info: max token length = 256 Aug 06 07:22:21 arch ollama[646637]: llama_model_load: vocab only - skipping tensors Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d --ctx-size 4096 --batch-size 512 --threads 8 --no-mmap --parallel 1 --port 34909" Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=sched.go:481 msg="loaded runners" count=1 Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.486+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.503+03:00 level=INFO source=runner.go:815 msg="starting go runner" Aug 06 07:22:21 arch ollama[646637]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.520+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.521+03:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:34909" Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: loaded meta data with 32 key-value pairs and 399 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d (version GGUF V3 (latest)) Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 0: general.architecture str = qwen3 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 1: general.type str = model Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 2: general.name str = DeepSeek R1 0528 Qwen3 8B Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-0528-Qwen3 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 4: general.size_label str = 8B Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 5: general.license str = mit Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 6: qwen3.block_count u32 = 36 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 7: qwen3.context_length u32 = 131072 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 8: qwen3.embedding_length u32 = 4096 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 12288 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 16: qwen3.rope.scaling.type str = yarn Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 17: qwen3.rope.scaling.factor f32 = 4.000000 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 18: qwen3.rope.scaling.original_context_length u32 = 32768 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 19: tokenizer.ggml.model str = gpt2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 20: tokenizer.ggml.pre str = qwen2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 23: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 151643 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 151645 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 151645 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 27: tokenizer.ggml.add_bos_token bool = false Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 28: tokenizer.ggml.add_eos_token bool = false Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 29: tokenizer.chat_template str = {% if not add_generation_prompt is de... Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 30: general.quantization_version u32 = 2 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - kv 31: general.file_type u32 = 15 Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type f32: 145 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type f16: 36 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q4_K: 199 tensors Aug 06 07:22:21 arch ollama[646637]: llama_model_loader: - type q6_K: 19 tensors Aug 06 07:22:21 arch ollama[646637]: print_info: file format = GGUF V3 (latest) Aug 06 07:22:21 arch ollama[646637]: print_info: file type = Q4_K - Medium Aug 06 07:22:21 arch ollama[646637]: print_info: file size = 4.86 GiB (5.10 BPW) Aug 06 07:22:21 arch ollama[646637]: load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect Aug 06 07:22:21 arch ollama[646637]: load: special tokens cache size = 28 Aug 06 07:22:21 arch ollama[646637]: load: token to piece cache size = 0.9311 MB Aug 06 07:22:21 arch ollama[646637]: print_info: arch = qwen3 Aug 06 07:22:21 arch ollama[646637]: print_info: vocab_only = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: n_ctx_train = 131072 Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd = 4096 Aug 06 07:22:21 arch ollama[646637]: print_info: n_layer = 36 Aug 06 07:22:21 arch ollama[646637]: print_info: n_head = 32 Aug 06 07:22:21 arch ollama[646637]: print_info: n_head_kv = 8 Aug 06 07:22:21 arch ollama[646637]: print_info: n_rot = 128 Aug 06 07:22:21 arch ollama[646637]: print_info: n_swa = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: n_swa_pattern = 1 Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_head_k = 128 Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_head_v = 128 Aug 06 07:22:21 arch ollama[646637]: print_info: n_gqa = 4 Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_k_gqa = 1024 Aug 06 07:22:21 arch ollama[646637]: print_info: n_embd_v_gqa = 1024 Aug 06 07:22:21 arch ollama[646637]: print_info: f_norm_eps = 0.0e+00 Aug 06 07:22:21 arch ollama[646637]: print_info: f_norm_rms_eps = 1.0e-06 Aug 06 07:22:21 arch ollama[646637]: print_info: f_clamp_kqv = 0.0e+00 Aug 06 07:22:21 arch ollama[646637]: print_info: f_max_alibi_bias = 0.0e+00 Aug 06 07:22:21 arch ollama[646637]: print_info: f_logit_scale = 0.0e+00 Aug 06 07:22:21 arch ollama[646637]: print_info: f_attn_scale = 0.0e+00 Aug 06 07:22:21 arch ollama[646637]: print_info: n_ff = 12288 Aug 06 07:22:21 arch ollama[646637]: print_info: n_expert = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: n_expert_used = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: causal attn = 1 Aug 06 07:22:21 arch ollama[646637]: print_info: pooling type = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: rope type = 2 Aug 06 07:22:21 arch ollama[646637]: print_info: rope scaling = yarn Aug 06 07:22:21 arch ollama[646637]: print_info: freq_base_train = 1000000.0 Aug 06 07:22:21 arch ollama[646637]: print_info: freq_scale_train = 0.25 Aug 06 07:22:21 arch ollama[646637]: print_info: n_ctx_orig_yarn = 32768 Aug 06 07:22:21 arch ollama[646637]: print_info: rope_finetuned = unknown Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_conv = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_inner = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_d_state = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_dt_rank = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: ssm_dt_b_c_rms = 0 Aug 06 07:22:21 arch ollama[646637]: print_info: model type = 8B Aug 06 07:22:21 arch ollama[646637]: print_info: model params = 8.19 B Aug 06 07:22:21 arch ollama[646637]: print_info: general.name = DeepSeek R1 0528 Qwen3 8B Aug 06 07:22:21 arch ollama[646637]: print_info: vocab type = BPE Aug 06 07:22:21 arch ollama[646637]: print_info: n_vocab = 151936 Aug 06 07:22:21 arch ollama[646637]: print_info: n_merges = 151387 Aug 06 07:22:21 arch ollama[646637]: print_info: BOS token = 151643 '<｜begin▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOS token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOT token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: PAD token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: LF token = 198 'Ċ' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM MID token = 151660 '<|fim_middle|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM REP token = 151663 '<|repo_name|>' Aug 06 07:22:21 arch ollama[646637]: print_info: FIM SEP token = 151664 '<|file_sep|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151645 '<｜end▁of▁sentence｜>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151662 '<|fim_pad|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151663 '<|repo_name|>' Aug 06 07:22:21 arch ollama[646637]: print_info: EOG token = 151664 '<|file_sep|>' Aug 06 07:22:21 arch ollama[646637]: print_info: max token length = 256 Aug 06 07:22:21 arch ollama[646637]: load_tensors: loading model tensors, this can take a while... (mmap = false) Aug 06 07:22:21 arch ollama[646637]: load_tensors: CPU model buffer size = 4977.62 MiB Aug 06 07:22:21 arch ollama[646637]: time=2025-08-06T07:22:21.737+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Aug 06 07:22:27 arch ollama[646637]: llama_context: constructing llama_context Aug 06 07:22:27 arch ollama[646637]: llama_context: n_seq_max = 1 Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx = 4096 Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx_per_seq = 4096 Aug 06 07:22:27 arch ollama[646637]: llama_context: n_batch = 512 Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ubatch = 512 Aug 06 07:22:27 arch ollama[646637]: llama_context: causal_attn = 1 Aug 06 07:22:27 arch ollama[646637]: llama_context: flash_attn = 0 Aug 06 07:22:27 arch ollama[646637]: llama_context: freq_base = 1000000.0 Aug 06 07:22:27 arch ollama[646637]: llama_context: freq_scale = 0.25 Aug 06 07:22:27 arch ollama[646637]: llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized Aug 06 07:22:27 arch ollama[646637]: llama_context: CPU output buffer size = 0.60 MiB Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified: kv_size = 4096, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1, padding = 32 Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified: CPU KV buffer size = 576.00 MiB Aug 06 07:22:27 arch ollama[646637]: llama_kv_cache_unified: KV self size = 576.00 MiB, K (f16): 288.00 MiB, V (f16): 288.00 MiB Aug 06 07:22:27 arch ollama[646637]: llama_context: CPU compute buffer size = 304.75 MiB Aug 06 07:22:27 arch ollama[646637]: llama_context: graph nodes = 1374 Aug 06 07:22:27 arch ollama[646637]: llama_context: graph splits = 1 Aug 06 07:22:27 arch ollama[646637]: time=2025-08-06T07:22:27.757+03:00 level=INFO source=server.go:637 msg="llama runner started in 6.27 seconds" Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.805+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="7.3 GiB" free_swap="14.9 GiB" Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.805+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[7.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.8 GiB" memory.required.partial="0 B" memory.required.kv="192.0 MiB" memory.required.allocations="[2.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB" Aug 06 07:40:46 arch ollama[646637]: gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' of type 4 (DEPRECATED) has 2880 elements per row, not a multiple of block size (0) Aug 06 07:40:46 arch ollama[646637]: gguf_init_from_file_impl: failed to read tensor info Aug 06 07:40:46 arch ollama[646637]: llama_model_load: error loading model: llama_model_loader: failed to load model from /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 Aug 06 07:40:46 arch ollama[646637]: llama_model_load_from_file_impl: failed to load model Aug 06 07:40:46 arch ollama[646637]: time=2025-08-06T07:40:46.883+03:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583" Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.381+03:00 level=INFO source=server.go:135 msg="system memory" total="15.0 GiB" free="7.2 GiB" free_swap="14.9 GiB" Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.381+03:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=25 layers.offload=0 layers.split="" memory.available="[7.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="2.8 GiB" memory.required.partial="0 B" memory.required.kv="192.0 MiB" memory.required.allocations="[2.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="256.0 MiB" memory.graph.partial="256.0 MiB" Aug 06 07:41:16 arch ollama[646637]: gguf_init_from_file_impl: tensor 'blk.0.ffn_down_exps.weight' of type 4 (DEPRECATED) has 2880 elements per row, not a multiple of block size (0) Aug 06 07:41:16 arch ollama[646637]: gguf_init_from_file_impl: failed to read tensor info Aug 06 07:41:16 arch ollama[646637]: llama_model_load: error loading model: llama_model_loader: failed to load model from /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 Aug 06 07:41:16 arch ollama[646637]: llama_model_load_from_file_impl: failed to load model Aug 06 07:41:16 arch ollama[646637]: time=2025-08-06T07:41:16.442+03:00 level=INFO source=sched.go:453 msg="NewLlamaServer failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 error="unable to load model: /usr/share/ollama/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583" ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.11.0

GiteaMirror added the bug label 2025-11-12 14:18:21 -06:00

GiteaMirror closed this issue

2025-11-12 14:18:21 -06:00

GiteaMirror commented

2025-11-12 14:18:22 -06:00

@rick-github commented on GitHub (Aug 6, 2025):

Upgrade ollama to at least 0.11.2.

@rick-github commented on GitHub (Aug 6, 2025): Upgrade ollama to at least [0.11.2]( https://github.com/ollama/ollama/releases/tag/v0.11.2).

GiteaMirror referenced this issue

2025-11-12 16:09:57 -06:00

[PR #7764] [MERGED] Fix minor typo in import.md #11248

Sign in to join this conversation.

Branches Tags

main

jessegross/batching

hoyyeva/fix-launch-app-process-reap

pdevine/manifest-list

hoyyeva/launch-page-update

codex/fix-codex-model-metadata-warning

hoyyeva/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

brucemacd/download-before-remove

parth/update-claude-docs

parth-anthropic-reference-images-path

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama-ollama#7764