github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8919] unexpected stop when running deepseek-r1:1.58bit #67840

New Issue
Closed
opened 2026-05-04 11:50:16 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 11:50:16 -05:00
Owner
Copy Link

Originally created by @Itsanewday on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8919

What is the issue?

I run the deepseek-r1:1.58bit model according to https://github.com/ollama/ollama/issues/8624#issuecomment-2631346462.
It worked when I tested with simple/short questions. But the model just stop when I asked a long question.
What should I do,

Relevant log output

time=2025-02-07T15:35:54.155+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=80 layers.model=62 layers.offload=62 layers.split=31,31 memory.available="[78.8 GiB 78.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="144.6 GiB" memory.required.partial="144.6 GiB" memory.required.kv="9.5 GiB" memory.required.allocations="[72.2 GiB 72.4 GiB]" memory.weights.total="138.9 GiB" memory.weights.repeating="138.2 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="1.5 GiB" memory.graph.partial="1.5 GiB"
time=2025-02-07T15:35:54.156+08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-a542caee8df72af41ad48d75b94adacb5fbc61856930460bd599d835400fb3b6 --ctx-size 2048 --batch-size 1024 --n-gpu-layers 80 --threads 48 --parallel 1 --tensor-split 31,31 --port 39693"
time=2025-02-07T15:35:54.156+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-07T15:35:54.156+08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
time=2025-02-07T15:35:54.157+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error"
time=2025-02-07T15:35:54.202+08:00 level=INFO source=runner.go:936 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 CUDA devices:
  Device 0: NVIDIA A800-SXM4-80GB, compute capability 8.0, VMM: yes
  Device 1: NVIDIA A800-SXM4-80GB, compute capability 8.0, VMM: yes
time=2025-02-07T15:35:54.407+08:00 level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=48
time=2025-02-07T15:35:54.408+08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:39693"
llama_load_model_from_file: using device CUDA0 (NVIDIA A800-SXM4-80GB) - 80732 MiB free
llama_load_model_from_file: using device CUDA1 (NVIDIA A800-SXM4-80GB) - 80732 MiB free
llama_model_loader: loaded meta data with 52 key-value pairs and 1025 tensors from /root/.ollama/models/blobs/sha256-a542caee8df72af41ad48d75b94adacb5fbc61856930460bd599d835400fb3b6 (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              = deepseek2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = DeepSeek R1 BF16
llama_model_loader: - kv   3:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   4:                         general.size_label str              = 256x20B
llama_model_loader: - kv   5:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   6:                      deepseek2.block_count u32              = 61
llama_model_loader: - kv   7:                   deepseek2.context_length u32              = 163840
llama_model_loader: - kv   8:                 deepseek2.embedding_length u32              = 7168
llama_model_loader: - kv   9:              deepseek2.feed_forward_length u32              = 18432
llama_model_loader: - kv  10:             deepseek2.attention.head_count u32              = 128
llama_model_loader: - kv  11:          deepseek2.attention.head_count_kv u32              = 128
llama_model_loader: - kv  12:                   deepseek2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  13: deepseek2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                deepseek2.expert_used_count u32              = 8
llama_model_loader: - kv  15:        deepseek2.leading_dense_block_count u32              = 3
llama_model_loader: - kv  16:                       deepseek2.vocab_size u32              = 129280
llama_model_loader: - kv  17:            deepseek2.attention.q_lora_rank u32              = 1536
llama_model_loader: - kv  18:           deepseek2.attention.kv_lora_rank u32              = 512
llama_model_loader: - kv  19:             deepseek2.attention.key_length u32              = 192
llama_model_loader: - kv  20:           deepseek2.attention.value_length u32              = 128
llama_model_loader: - kv  21:       deepseek2.expert_feed_forward_length u32              = 2048
llama_model_loader: - kv  22:                     deepseek2.expert_count u32              = 256
llama_model_loader: - kv  23:              deepseek2.expert_shared_count u32              = 1
llama_model_loader: - kv  24:             deepseek2.expert_weights_scale f32              = 2.500000
llama_model_loader: - kv  25:              deepseek2.expert_weights_norm bool             = true
llama_model_loader: - kv  26:               deepseek2.expert_gating_func u32              = 2
llama_model_loader: - kv  27:             deepseek2.rope.dimension_count u32              = 64
llama_model_loader: - kv  28:                deepseek2.rope.scaling.type str              = yarn
llama_model_loader: - kv  29:              deepseek2.rope.scaling.factor f32              = 40.000000
llama_model_loader: - kv  30: deepseek2.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  31: deepseek2.rope.scaling.yarn_log_multiplier f32              = 0.100000
llama_model_loader: - kv  32:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  33:                         tokenizer.ggml.pre str              = deepseek-v3
time=2025-02-07T15:35:54.659+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv  34:                      tokenizer.ggml.tokens arr[str,129280]  = ["<｜begin▁of▁sentence｜>", "<�...
llama_model_loader: - kv  35:                  tokenizer.ggml.token_type arr[i32,129280]  = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  36:                      tokenizer.ggml.merges arr[str,127741]  = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e...
llama_model_loader: - kv  37:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  38:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  39:            tokenizer.ggml.padding_token_id u32              = 128815
llama_model_loader: - kv  40:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  41:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  42:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  43:               general.quantization_version u32              = 2
llama_model_loader: - kv  44:                          general.file_type u32              = 24
llama_model_loader: - kv  45:                      quantize.imatrix.file str              = DeepSeek-R1.imatrix
llama_model_loader: - kv  46:                   quantize.imatrix.dataset str              = /training_data/calibration_datav3.txt
llama_model_loader: - kv  47:             quantize.imatrix.entries_count i32              = 720
llama_model_loader: - kv  48:              quantize.imatrix.chunks_count i32              = 124
llama_model_loader: - kv  49:                                   split.no u16              = 0
llama_model_loader: - kv  50:                        split.tensors.count i32              = 1025
llama_model_loader: - kv  51:                                split.count u16              = 0
llama_model_loader: - type  f32:  361 tensors
llama_model_loader: - type q4_K:  190 tensors
llama_model_loader: - type q5_K:  116 tensors
llama_model_loader: - type q6_K:  184 tensors
llama_model_loader: - type iq2_xxs:    6 tensors
llama_model_loader: - type iq1_s:  168 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 819
llm_load_vocab: token to piece cache size = 0.8223 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = deepseek2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 129280
llm_load_print_meta: n_merges         = 127741
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 163840
llm_load_print_meta: n_embd           = 7168
llm_load_print_meta: n_layer          = 61
llm_load_print_meta: n_head           = 128
llm_load_print_meta: n_head_kv        = 128
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 192
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 24576
llm_load_print_meta: n_embd_v_gqa     = 16384
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 18432
llm_load_print_meta: n_expert         = 256
llm_load_print_meta: n_expert_used    = 8
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = yarn
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 0.025
llm_load_print_meta: n_ctx_orig_yarn  = 4096
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 671B
llm_load_print_meta: model ftype      = IQ1_S - 1.5625 bpw
llm_load_print_meta: model params     = 671.03 B
llm_load_print_meta: model size       = 130.60 GiB (1.67 BPW)
llm_load_print_meta: general.name     = DeepSeek R1 BF16
llm_load_print_meta: BOS token        = 0 '<｜begin▁of▁sentence｜>'
llm_load_print_meta: EOS token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOT token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: PAD token        = 128815 '<｜PAD▁TOKEN｜>'
llm_load_print_meta: LF token         = 131 'Ä'
llm_load_print_meta: FIM PRE token    = 128801 '<｜fim▁begin｜>'
llm_load_print_meta: FIM SUF token    = 128800 '<｜fim▁hole｜>'
llm_load_print_meta: FIM MID token    = 128802 '<｜fim▁end｜>'
llm_load_print_meta: EOG token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: max token length = 256
llm_load_print_meta: n_layer_dense_lead   = 3
llm_load_print_meta: n_lora_q             = 1536
llm_load_print_meta: n_lora_kv            = 512
llm_load_print_meta: n_ff_exp             = 2048
llm_load_print_meta: n_expert_shared      = 1
llm_load_print_meta: expert_weights_scale = 2.5
llm_load_print_meta: expert_weights_norm  = 1
llm_load_print_meta: expert_gating_func   = sigmoid
llm_load_print_meta: rope_yarn_log_mul    = 0.1000
llm_load_tensors: offloading 61 repeating layers to GPU
llm_load_tensors: offloading output layer to GPU
llm_load_tensors: offloaded 62/62 layers to GPU
llm_load_tensors:   CPU_Mapped model buffer size =   497.11 MiB
llm_load_tensors:        CUDA0 model buffer size = 65208.70 MiB
llm_load_tensors:        CUDA1 model buffer size = 68024.25 MiB

OS

ubuntu

GPU

a100 * 2

CPU

No response

Ollama version

No response

Originally created by @Itsanewday on GitHub (Feb 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8919 ### What is the issue? I run the deepseek-r1:1.58bit model according to https://github.com/ollama/ollama/issues/8624#issuecomment-2631346462. It worked when I tested with simple/short questions. But the model just stop when I asked a long question. What should I do, ### Relevant log output ```time=2025-02-07T15:35:54.154+08:00 level=INFO source=server.go:104 msg="system memory" total="503.7 GiB" free="452.2 GiB" free_swap="8.0 GiB" time=2025-02-07T15:35:54.155+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=80 layers.model=62 layers.offload=62 layers.split=31,31 memory.available="[78.8 GiB 78.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="144.6 GiB" memory.required.partial="144.6 GiB" memory.required.kv="9.5 GiB" memory.required.allocations="[72.2 GiB 72.4 GiB]" memory.weights.total="138.9 GiB" memory.weights.repeating="138.2 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="1.5 GiB" memory.graph.partial="1.5 GiB" time=2025-02-07T15:35:54.156+08:00 level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-a542caee8df72af41ad48d75b94adacb5fbc61856930460bd599d835400fb3b6 --ctx-size 2048 --batch-size 1024 --n-gpu-layers 80 --threads 48 --parallel 1 --tensor-split 31,31 --port 39693" time=2025-02-07T15:35:54.156+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-07T15:35:54.156+08:00 level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2025-02-07T15:35:54.157+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" time=2025-02-07T15:35:54.202+08:00 level=INFO source=runner.go:936 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 2 CUDA devices: Device 0: NVIDIA A800-SXM4-80GB, compute capability 8.0, VMM: yes Device 1: NVIDIA A800-SXM4-80GB, compute capability 8.0, VMM: yes time=2025-02-07T15:35:54.407+08:00 level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=48 time=2025-02-07T15:35:54.408+08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:39693" llama_load_model_from_file: using device CUDA0 (NVIDIA A800-SXM4-80GB) - 80732 MiB free llama_load_model_from_file: using device CUDA1 (NVIDIA A800-SXM4-80GB) - 80732 MiB free llama_model_loader: loaded meta data with 52 key-value pairs and 1025 tensors from /root/.ollama/models/blobs/sha256-a542caee8df72af41ad48d75b94adacb5fbc61856930460bd599d835400fb3b6 (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 = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = DeepSeek R1 BF16 llama_model_loader: - kv 3: general.quantized_by str = Unsloth llama_model_loader: - kv 4: general.size_label str = 256x20B llama_model_loader: - kv 5: general.repo_url str = https://huggingface.co/unsloth llama_model_loader: - kv 6: deepseek2.block_count u32 = 61 llama_model_loader: - kv 7: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 8: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 9: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 10: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 11: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 12: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 13: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 14: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 15: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 16: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 17: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 18: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 19: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 20: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 21: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 22: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 23: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 24: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 25: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 26: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 27: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 28: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 29: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 30: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 31: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 32: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 33: tokenizer.ggml.pre str = deepseek-v3 time=2025-02-07T15:35:54.659+08:00 level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 34: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 35: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 36: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 37: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 38: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 39: tokenizer.ggml.padding_token_id u32 = 128815 llama_model_loader: - kv 40: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 41: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 42: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 43: general.quantization_version u32 = 2 llama_model_loader: - kv 44: general.file_type u32 = 24 llama_model_loader: - kv 45: quantize.imatrix.file str = DeepSeek-R1.imatrix llama_model_loader: - kv 46: quantize.imatrix.dataset str = /training_data/calibration_datav3.txt llama_model_loader: - kv 47: quantize.imatrix.entries_count i32 = 720 llama_model_loader: - kv 48: quantize.imatrix.chunks_count i32 = 124 llama_model_loader: - kv 49: split.no u16 = 0 llama_model_loader: - kv 50: split.tensors.count i32 = 1025 llama_model_loader: - kv 51: split.count u16 = 0 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 190 tensors llama_model_loader: - type q5_K: 116 tensors llama_model_loader: - type q6_K: 184 tensors llama_model_loader: - type iq2_xxs: 6 tensors llama_model_loader: - type iq1_s: 168 tensors llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 819 llm_load_vocab: token to piece cache size = 0.8223 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = deepseek2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 129280 llm_load_print_meta: n_merges = 127741 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 163840 llm_load_print_meta: n_embd = 7168 llm_load_print_meta: n_layer = 61 llm_load_print_meta: n_head = 128 llm_load_print_meta: n_head_kv = 128 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 192 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 24576 llm_load_print_meta: n_embd_v_gqa = 16384 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 18432 llm_load_print_meta: n_expert = 256 llm_load_print_meta: n_expert_used = 8 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = yarn llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 0.025 llm_load_print_meta: n_ctx_orig_yarn = 4096 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 671B llm_load_print_meta: model ftype = IQ1_S - 1.5625 bpw llm_load_print_meta: model params = 671.03 B llm_load_print_meta: model size = 130.60 GiB (1.67 BPW) llm_load_print_meta: general.name = DeepSeek R1 BF16 llm_load_print_meta: BOS token = 0 '<｜begin▁of▁sentence｜>' llm_load_print_meta: EOS token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOT token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: PAD token = 128815 '<｜PAD▁TOKEN｜>' llm_load_print_meta: LF token = 131 'Ä' llm_load_print_meta: FIM PRE token = 128801 '<｜fim▁begin｜>' llm_load_print_meta: FIM SUF token = 128800 '<｜fim▁hole｜>' llm_load_print_meta: FIM MID token = 128802 '<｜fim▁end｜>' llm_load_print_meta: EOG token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: max token length = 256 llm_load_print_meta: n_layer_dense_lead = 3 llm_load_print_meta: n_lora_q = 1536 llm_load_print_meta: n_lora_kv = 512 llm_load_print_meta: n_ff_exp = 2048 llm_load_print_meta: n_expert_shared = 1 llm_load_print_meta: expert_weights_scale = 2.5 llm_load_print_meta: expert_weights_norm = 1 llm_load_print_meta: expert_gating_func = sigmoid llm_load_print_meta: rope_yarn_log_mul = 0.1000 llm_load_tensors: offloading 61 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 62/62 layers to GPU llm_load_tensors: CPU_Mapped model buffer size = 497.11 MiB llm_load_tensors: CUDA0 model buffer size = 65208.70 MiB llm_load_tensors: CUDA1 model buffer size = 68024.25 MiB ``` ### OS ubuntu ### GPU a100 * 2 ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-04 11:50:16 -05:00
GiteaMirror commented 2026-05-04 11:50:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2025):

You don't include the bit where the model stops, but I'm going to guess k-shift. https://github.com/ollama/ollama/issues/5975

<!-- gh-comment-id:2642284186 --> @rick-github commented on GitHub (Feb 7, 2025): You don't include the bit where the model stops, but I'm going to guess k-shift. https://github.com/ollama/ollama/issues/5975
GiteaMirror commented 2026-05-04 11:50:28 -05:00
Author
Owner
Copy Link

@Itsanewday commented on GitHub (Feb 11, 2025):

You don't include the bit where the model stops, but I'm going to guess k-shift. #5975

Thank you very much. I created a model file from the 1.58bit model(147G)，and modified the num_ctx and num_predict parameters according [#5975]. I noticed that the new model takes up about double the size (280 GB). Is this normal? I can only use two GPUs, which cannot accommodate the entire model, resulting in very slow performance. What can I do to improve this situation?

<!-- gh-comment-id:2649759594 --> @Itsanewday commented on GitHub (Feb 11, 2025): > You don't include the bit where the model stops, but I'm going to guess k-shift. [#5975](https://github.com/ollama/ollama/issues/5975) Thank you very much. I created a model file from the 1.58bit model(147G)，and modified the num_ctx and num_predict parameters according [#5975]. I noticed that the new model takes up about double the size (280 GB). Is this normal? I can only use two GPUs, which cannot accommodate the entire model, resulting in very slow performance. What can I do to improve this situation?
GiteaMirror commented 2026-05-04 11:50:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 11, 2025):

Reduce num_ctx. https://github.com/ollama/ollama/issues/5975#issuecomment-2548969872

<!-- gh-comment-id:2650310075 --> @rick-github commented on GitHub (Feb 11, 2025): Reduce `num_ctx`. https://github.com/ollama/ollama/issues/5975#issuecomment-2548969872
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#67840
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?