github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-25 17:21:00 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #284] UI formatting bug #115332

New Issue
Closed
opened 2026-05-20 17:02:07 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-20 17:02:07 -05:00
Owner
Copy Link
Copy Source

Originally created by @iukea1 on GitHub (Dec 27, 2023).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/284

Bug Report

The UI is not formatting the responses back from multiple different LLMs correctly

Description

Bug Summary:
[Provide a brief but clear summary of the bug]

Steps to Reproduce:
[Outline the steps to reproduce the bug. Be as detailed as possible.]

Expected Behavior:
[Describe what you expected to happen.]

Actual Behavior:
[Describe what actually happened.]

Environment

  • Operating System: [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]
  • Browser (if applicable): [e.g., Chrome 100.0, Firefox 98.0]

Reproduction Details

Confirmation:

  • I have read and followed all the instructions provided in the README.md.
  • I have reviewed the troubleshooting.md document.
  • I have included the browser console logs.
  • I have included the Docker container logs.

Logs and Screenshots

image

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:

2-27 00:45:40 ollama        | 
2023-12-27 00:45:40 ollama        | Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option. [/INST]
2023-12-27 00:45:40 ollama        |  repeat_last_n:64 repeat_penalty:1.1 seed:-1 stop:[</s> [INST] [/INST] <<SYS>> <</SYS>>] stream:true temperature:0.8 tfs_z:1 top_k:40 top_p:0.9 typical_p:1]
2023-12-27 00:45:40 ollama-webui  | chat
2023-12-27 00:45:40 ollama-webui  | INFO:     172.20.0.1:43068 - "POST /chat HTTP/1.1" 200 OK
2023-12-27 00:45:50 ollama        | {"timestamp":1703666750,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":57810,"status":200,"method":"POST","path":"/completion","params":{}}
2023-12-27 00:45:50 ollama        | [GIN] 2023/12/27 - 08:45:50 | 200 |    13.648164s |      172.20.0.3 | POST     "/api/chat"
2023-12-27 00:45:50 ollama        | {"timestamp":1703666750,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43382,"status":200,"method":"HEAD","path":"/","params":{}}
2023-12-27 00:45:50 ollama        | 2023/12/27 08:45:50 routes.go:105: changing loaded model
2023-12-27 00:45:51 ollama        | 2023/12/27 08:45:51 llama.go:455: signal: killed
2023-12-27 00:45:51 ollama        | 2023/12/27 08:45:51 llama.go:529: llama runner stopped successfully
2023-12-27 00:45:51 ollama        | 2023/12/27 08:45:51 llama.go:300: 22003 MB VRAM available, loading up to 87 GPU layers
2023-12-27 00:45:51 ollama        | {{false 2048 512 0 -1 0 false true false false true false true 0 0 0} 0 -1 -1 40 0.9 1 1 64 0.8 1.1 0 0 0 5 0.1 true [</s> [INST] [/INST] <<SYS>> <</SYS>>]} 0 0
2023-12-27 00:45:51 ollama        | [--model /root/.ollama/models/blobs/sha256:a035193675f3ea5c5c97c143ba7be504ebbf002a2c53822819988ac689d70783 --ctx-size 2048 --batch-size 512 --n-gpu-layers 87 --embedding]
2023-12-27 00:45:51 ollama        | 2023/12/27 08:45:51 llama.go:440: starting llama runner
2023-12-27 00:45:51 ollama        | 2023/12/27 08:45:51 llama.go:498: waiting for llama runner to start responding
2023-12-27 00:45:51 ollama        | ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
2023-12-27 00:45:51 ollama        | ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
2023-12-27 00:45:51 ollama        | ggml_init_cublas: found 1 CUDA devices:
2023-12-27 00:45:51 ollama        |   Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9
2023-12-27 00:45:51 ollama        | {"timestamp":1703666751,"level":"INFO","function":"main","line":2667,"message":"build info","build":468,"commit":"a7aee47"}
2023-12-27 00:45:51 ollama        | {"timestamp":1703666751,"level":"INFO","function":"main","line":2670,"message":"system info","n_threads":10,"n_threads_batch":-1,"total_threads":20,"system_info":"AVX = 1 | 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 | "}
2023-12-27 00:45:51 ollama        | llama_model_loader: loaded meta data with 23 key-value pairs and 363 tensors from /root/.ollama/models/blobs/sha256:a035193675f3ea5c5c97c143ba7be504ebbf002a2c53822819988ac689d70783 (version GGUF V3 (latest))
2023-12-27 00:45:51 ollama        | llama_model_loader: - tensor    0:                token_embd.weight q4_K     [  5120, 32000,     1,     1 ]
2023-12-27 00:45:51 ollama        | llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  5120,     1,     1,     1 ]
2023-12-27 00:45:51 ollama        | llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]
2023-12-27 00:45:51 ollama        | llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q4_K     [  5120, 13824,     1,     1 ]
2023-12-27 00:45:51 ollama        | llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q4_K     [  5120, 13824,     1,     1 ]
2
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,61249]   = ["▁ t", "e r", "i n", "▁ a", "e n...
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 0
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  19:               tokenizer.ggml.add_bos_token bool             = true
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  20:               tokenizer.ggml.add_eos_token bool             = false
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  21:                    tokenizer.chat_template str              = {% if messages[0]['role'] == 'system'...
2023-12-27 00:45:51 ollama        | llama_model_loader: - kv  22:               general.quantization_version u32              = 2
2023-12-27 00:45:51 ollama        | llama_model_loader: - type  f32:   81 tensors
2023-12-27 00:45:51 ollama        | llama_model_loader: - type q4_K:  241 tensors
2023-12-27 00:45:51 ollama        | llama_model_loader: - type q6_K:   41 tensors
2023-12-27 00:45:51 ollama        | llm_load_vocab: special tokens definition check successful ( 259/32000 ).
2023-12-27 00:45:51 ollama        | llm_load_print_meta: format           = GGUF V3 (latest)
2023-12-27 00:45:51 ollama        | llm_load_print_meta: arch             = llama
2023-12-27 00:45:51 ollama        | llm_load_print_meta: vocab type       = SPM
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_vocab          = 32000
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_merges         = 0
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_ctx_train      = 4096
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_embd           = 5120
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_head           = 40
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_head_kv        = 40
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_layer          = 40
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_rot            = 128
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_gqa            = 1
2023-12-27 00:45:51 ollama        | llm_load_print_meta: f_norm_eps       = 0.0e+00
2023-12-27 00:45:51 ollama        | llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
2023-12-27 00:45:51 ollama        | llm_load_print_meta: f_clamp_kqv      = 0.0e+00
2023-12-27 00:45:51 ollama        | llm_load_print_meta: f_max_alibi_bias = 0.0e+00
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_ff             = 13824
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_expert         = 0
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_expert_used    = 0
2023-12-27 00:45:51 ollama        | llm_load_print_meta: rope scaling     = linear
2023-12-27 00:45:51 ollama        | llm_load_print_meta: freq_base_train  = 10000.0
2023-12-27 00:45:51 ollama        | llm_load_print_meta: freq_scale_train = 1
2023-12-27 00:45:51 ollama        | llm_load_print_meta: n_yarn_orig_ctx  = 4096
2023-12-27 00:45:51 ollama        | llm_load_print_meta: rope_finetuned   = unknown
2023-12-27 00:45:51 ollama        | llm_load_print_meta: model type       = 13B
2023-12-27 00:45:51 ollama        | llm_load_print_meta: model ftype      = Q4_K - Medium
2023-12-27 00:45:51 ollama        | llm_load_print_meta: model params     = 13.02 B
2023-12-27 00:45:51 ollama        | llm_load_print_meta: model size       = 7.33 GiB (4.83 BPW) 
2023-12-27 00:45:51 ollama        | llm_load_print_meta: general.name     = LLaMA v2
2023-12-27 00:45:51 ollama        | llm_load_print_meta: BOS token        = 1 '<s>'
2023-12-27 00:45:51 ollama        | llm_load_print_meta: EOS token        = 2 '</s>'
2023-12-27 00:45:51 ollama        | llm_load_print_meta: UNK token        = 0 '<unk>'
2023-12-27 00:45:51 ollama        | llm_load_print_meta: LF token         = 13 '<0x0A>'
2023-12-27 00:45:51 ollama        | llm_load_tensors: ggml ctx size =    0.14 MiB
2023-12-27 00:45:51 ollama        | llm_load_tensors: using CUDA for GPU acceleration
2023-12-27 00:45:51 ollama        | llm_load_tensors: mem required  =   88.03 MiB
2023-12-27 00:45:51 ollama        | llm_load_tensors: offloading 40 repeating layers to GPU
2023-12-27 00:45:51 ollama        | llm_load_tensors: offloading non-repeating layers to GPU
2023-12-27 00:45:51 ollama        | llm_load_tensors: offloaded 41/41 layers to GPU
2023-12-27 00:45:51 ollama        | llm_load_tensors: VRAM used: 7412.96 MiB
2023-12-27 00:45:52 ollama        | ....................................................................................................
2023-12-27 00:45:52 ollama        | llama_new_context_with_model: n_ctx      = 2048
2023-12-27 00:45:52 ollama        | llama_new_context_with_model: freq_base  = 10000.0
2023-12-27 00:45:52 ollama        | llama_new_context_with_model: freq_scale = 1
2023-12-27 00:45:53 ollama        | llama_kv_cache_init: VRAM kv self = 1600.00 MB
2023-12-27 00:45:53 ollama        | llama_new_context_with_model: KV self size  = 1600.00 MiB, K (f16):  800.00 MiB, V (f16):  800.00 MiB
2023-12-27 00:45:53 ollama        | llama_build_graph: non-view tensors processed: 844/844
2023-12-27 00:45:53 ollama        | llama_new_context_with_model: compute buffer total size = 197.19 MiB
2023-12-27 00:45:53 ollama        | llama_new_context_with_model: VRAM scratch buffer: 194.00 MiB
2023-12-27 00:45:53 ollama        | llama_new_context_with_model: total VRAM used: 9206.96 MiB (model: 7412.96 MiB, context: 1794.00 MiB)
2023-12-27 00:45:53 ollama        | {"timestamp":1703666753,"level":"INFO","function":"main","line":3097,"message":"HTTP server listening","port":"60163","hostname":"127.0.0.1"}
2023-12-27 00:45:53 ollama        | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43198,"status":200,"method":"HEAD","path":"/","params":{}}
2023-12-27 00:45:53 ollama        | 2023/12/27 08:45:53 llama.go:512: llama runner started in 1.800561 seconds
2023-12-27 00:45:53 ollama        | 2023/12/27 08:45:53 llama.go:581: loaded 0 images
2023-12-27 00:45:53 ollama        | map[frequency_penalty:0 image_data:[] main_gpu:0 mirostat:0 mirostat_eta:0.1 mirostat_tau:5 n_keep:0 n_predict:-1 penalize_nl:true presence_penalty:0 prompt:[INST] <<SYS>><</SYS>>
2023-12-27 00:45:53 ollama        | 
2023-12-27 00:45:53 ollama        | Generate a brief 3-5 word title for this question, excluding the term 'title.' Then, please reply with only the title: Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option. [/INST]
2023-12-27 00:45:53 ollama        |  repeat_last_n:64 repeat_penalty:1.1 seed:-1 stop:[</s> [INST] [/INST] <<SYS>> <</SYS>>] stream:true temperature:0.8 tfs_z:1 top_k:40 top_p:0.9 typical_p:1]
2023-12-27 00:45:53 ollama        | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43198,"status":200,"method":"POST","path":"/completion","params":{}}
2023-12-27 00:45:53 ollama        | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43202,"status":200,"method":"POST","path":"/tokenize","params":{}}
2023-12-27 00:45:53 ollama        | [GIN] 2023/12/27 - 08:45:53 | 200 |  3.096371564s |      172.20.0.3 | POST     "/api/generate"
2023-12-27 00:45:53 ollama-webui  | generate
Originally created by @iukea1 on GitHub (Dec 27, 2023). Original GitHub issue: https://github.com/open-webui/open-webui/issues/284 # Bug Report The UI is not formatting the responses back from multiple different LLMs correctly ## Description **Bug Summary:** [Provide a brief but clear summary of the bug] **Steps to Reproduce:** [Outline the steps to reproduce the bug. Be as detailed as possible.] **Expected Behavior:** [Describe what you expected to happen.] **Actual Behavior:** [Describe what actually happened.] ## Environment - **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04] - **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0] ## Reproduction Details **Confirmation:** - [ ] I have read and followed all the instructions provided in the README.md. - [ ] I have reviewed the troubleshooting.md document. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. ## Logs and Screenshots ![image](https://github.com/ollama-webui/ollama-webui/assets/35882815/d8030d95-ead6-4168-add9-26f0cc61c2fe) **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** ``` 2-27 00:45:40 ollama | 2023-12-27 00:45:40 ollama | Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option. [/INST] 2023-12-27 00:45:40 ollama | repeat_last_n:64 repeat_penalty:1.1 seed:-1 stop:[</s> [INST] [/INST] <<SYS>> <</SYS>>] stream:true temperature:0.8 tfs_z:1 top_k:40 top_p:0.9 typical_p:1] 2023-12-27 00:45:40 ollama-webui | chat 2023-12-27 00:45:40 ollama-webui | INFO: 172.20.0.1:43068 - "POST /chat HTTP/1.1" 200 OK 2023-12-27 00:45:50 ollama | {"timestamp":1703666750,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":57810,"status":200,"method":"POST","path":"/completion","params":{}} 2023-12-27 00:45:50 ollama | [GIN] 2023/12/27 - 08:45:50 | 200 | 13.648164s | 172.20.0.3 | POST "/api/chat" 2023-12-27 00:45:50 ollama | {"timestamp":1703666750,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43382,"status":200,"method":"HEAD","path":"/","params":{}} 2023-12-27 00:45:50 ollama | 2023/12/27 08:45:50 routes.go:105: changing loaded model 2023-12-27 00:45:51 ollama | 2023/12/27 08:45:51 llama.go:455: signal: killed 2023-12-27 00:45:51 ollama | 2023/12/27 08:45:51 llama.go:529: llama runner stopped successfully 2023-12-27 00:45:51 ollama | 2023/12/27 08:45:51 llama.go:300: 22003 MB VRAM available, loading up to 87 GPU layers 2023-12-27 00:45:51 ollama | {{false 2048 512 0 -1 0 false true false false true false true 0 0 0} 0 -1 -1 40 0.9 1 1 64 0.8 1.1 0 0 0 5 0.1 true [</s> [INST] [/INST] <<SYS>> <</SYS>>]} 0 0 2023-12-27 00:45:51 ollama | [--model /root/.ollama/models/blobs/sha256:a035193675f3ea5c5c97c143ba7be504ebbf002a2c53822819988ac689d70783 --ctx-size 2048 --batch-size 512 --n-gpu-layers 87 --embedding] 2023-12-27 00:45:51 ollama | 2023/12/27 08:45:51 llama.go:440: starting llama runner 2023-12-27 00:45:51 ollama | 2023/12/27 08:45:51 llama.go:498: waiting for llama runner to start responding 2023-12-27 00:45:51 ollama | ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no 2023-12-27 00:45:51 ollama | ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes 2023-12-27 00:45:51 ollama | ggml_init_cublas: found 1 CUDA devices: 2023-12-27 00:45:51 ollama | Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9 2023-12-27 00:45:51 ollama | {"timestamp":1703666751,"level":"INFO","function":"main","line":2667,"message":"build info","build":468,"commit":"a7aee47"} 2023-12-27 00:45:51 ollama | {"timestamp":1703666751,"level":"INFO","function":"main","line":2670,"message":"system info","n_threads":10,"n_threads_batch":-1,"total_threads":20,"system_info":"AVX = 1 | 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 | "} 2023-12-27 00:45:51 ollama | llama_model_loader: loaded meta data with 23 key-value pairs and 363 tensors from /root/.ollama/models/blobs/sha256:a035193675f3ea5c5c97c143ba7be504ebbf002a2c53822819988ac689d70783 (version GGUF V3 (latest)) 2023-12-27 00:45:51 ollama | llama_model_loader: - tensor 0: token_embd.weight q4_K [ 5120, 32000, 1, 1 ] 2023-12-27 00:45:51 ollama | llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 5120, 1, 1, 1 ] 2023-12-27 00:45:51 ollama | llama_model_loader: - tensor 2: blk.0.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ] 2023-12-27 00:45:51 ollama | llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ] 2023-12-27 00:45:51 ollama | llama_model_loader: - tensor 4: blk.0.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ] 2 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 11: tokenizer.ggml.model str = llama 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,61249] = ["▁ t", "e r", "i n", "▁ a", "e n... 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 19: tokenizer.ggml.add_bos_token bool = true 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 20: tokenizer.ggml.add_eos_token bool = false 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 21: tokenizer.chat_template str = {% if messages[0]['role'] == 'system'... 2023-12-27 00:45:51 ollama | llama_model_loader: - kv 22: general.quantization_version u32 = 2 2023-12-27 00:45:51 ollama | llama_model_loader: - type f32: 81 tensors 2023-12-27 00:45:51 ollama | llama_model_loader: - type q4_K: 241 tensors 2023-12-27 00:45:51 ollama | llama_model_loader: - type q6_K: 41 tensors 2023-12-27 00:45:51 ollama | llm_load_vocab: special tokens definition check successful ( 259/32000 ). 2023-12-27 00:45:51 ollama | llm_load_print_meta: format = GGUF V3 (latest) 2023-12-27 00:45:51 ollama | llm_load_print_meta: arch = llama 2023-12-27 00:45:51 ollama | llm_load_print_meta: vocab type = SPM 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_vocab = 32000 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_merges = 0 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_ctx_train = 4096 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_embd = 5120 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_head = 40 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_head_kv = 40 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_layer = 40 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_rot = 128 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_gqa = 1 2023-12-27 00:45:51 ollama | llm_load_print_meta: f_norm_eps = 0.0e+00 2023-12-27 00:45:51 ollama | llm_load_print_meta: f_norm_rms_eps = 1.0e-05 2023-12-27 00:45:51 ollama | llm_load_print_meta: f_clamp_kqv = 0.0e+00 2023-12-27 00:45:51 ollama | llm_load_print_meta: f_max_alibi_bias = 0.0e+00 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_ff = 13824 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_expert = 0 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_expert_used = 0 2023-12-27 00:45:51 ollama | llm_load_print_meta: rope scaling = linear 2023-12-27 00:45:51 ollama | llm_load_print_meta: freq_base_train = 10000.0 2023-12-27 00:45:51 ollama | llm_load_print_meta: freq_scale_train = 1 2023-12-27 00:45:51 ollama | llm_load_print_meta: n_yarn_orig_ctx = 4096 2023-12-27 00:45:51 ollama | llm_load_print_meta: rope_finetuned = unknown 2023-12-27 00:45:51 ollama | llm_load_print_meta: model type = 13B 2023-12-27 00:45:51 ollama | llm_load_print_meta: model ftype = Q4_K - Medium 2023-12-27 00:45:51 ollama | llm_load_print_meta: model params = 13.02 B 2023-12-27 00:45:51 ollama | llm_load_print_meta: model size = 7.33 GiB (4.83 BPW) 2023-12-27 00:45:51 ollama | llm_load_print_meta: general.name = LLaMA v2 2023-12-27 00:45:51 ollama | llm_load_print_meta: BOS token = 1 '<s>' 2023-12-27 00:45:51 ollama | llm_load_print_meta: EOS token = 2 '</s>' 2023-12-27 00:45:51 ollama | llm_load_print_meta: UNK token = 0 '<unk>' 2023-12-27 00:45:51 ollama | llm_load_print_meta: LF token = 13 '<0x0A>' 2023-12-27 00:45:51 ollama | llm_load_tensors: ggml ctx size = 0.14 MiB 2023-12-27 00:45:51 ollama | llm_load_tensors: using CUDA for GPU acceleration 2023-12-27 00:45:51 ollama | llm_load_tensors: mem required = 88.03 MiB 2023-12-27 00:45:51 ollama | llm_load_tensors: offloading 40 repeating layers to GPU 2023-12-27 00:45:51 ollama | llm_load_tensors: offloading non-repeating layers to GPU 2023-12-27 00:45:51 ollama | llm_load_tensors: offloaded 41/41 layers to GPU 2023-12-27 00:45:51 ollama | llm_load_tensors: VRAM used: 7412.96 MiB 2023-12-27 00:45:52 ollama | .................................................................................................... 2023-12-27 00:45:52 ollama | llama_new_context_with_model: n_ctx = 2048 2023-12-27 00:45:52 ollama | llama_new_context_with_model: freq_base = 10000.0 2023-12-27 00:45:52 ollama | llama_new_context_with_model: freq_scale = 1 2023-12-27 00:45:53 ollama | llama_kv_cache_init: VRAM kv self = 1600.00 MB 2023-12-27 00:45:53 ollama | llama_new_context_with_model: KV self size = 1600.00 MiB, K (f16): 800.00 MiB, V (f16): 800.00 MiB 2023-12-27 00:45:53 ollama | llama_build_graph: non-view tensors processed: 844/844 2023-12-27 00:45:53 ollama | llama_new_context_with_model: compute buffer total size = 197.19 MiB 2023-12-27 00:45:53 ollama | llama_new_context_with_model: VRAM scratch buffer: 194.00 MiB 2023-12-27 00:45:53 ollama | llama_new_context_with_model: total VRAM used: 9206.96 MiB (model: 7412.96 MiB, context: 1794.00 MiB) 2023-12-27 00:45:53 ollama | {"timestamp":1703666753,"level":"INFO","function":"main","line":3097,"message":"HTTP server listening","port":"60163","hostname":"127.0.0.1"} 2023-12-27 00:45:53 ollama | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43198,"status":200,"method":"HEAD","path":"/","params":{}} 2023-12-27 00:45:53 ollama | 2023/12/27 08:45:53 llama.go:512: llama runner started in 1.800561 seconds 2023-12-27 00:45:53 ollama | 2023/12/27 08:45:53 llama.go:581: loaded 0 images 2023-12-27 00:45:53 ollama | map[frequency_penalty:0 image_data:[] main_gpu:0 mirostat:0 mirostat_eta:0.1 mirostat_tau:5 n_keep:0 n_predict:-1 penalize_nl:true presence_penalty:0 prompt:[INST] <<SYS>><</SYS>> 2023-12-27 00:45:53 ollama | 2023-12-27 00:45:53 ollama | Generate a brief 3-5 word title for this question, excluding the term 'title.' Then, please reply with only the title: Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option. [/INST] 2023-12-27 00:45:53 ollama | repeat_last_n:64 repeat_penalty:1.1 seed:-1 stop:[</s> [INST] [/INST] <<SYS>> <</SYS>>] stream:true temperature:0.8 tfs_z:1 top_k:40 top_p:0.9 typical_p:1] 2023-12-27 00:45:53 ollama | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43198,"status":200,"method":"POST","path":"/completion","params":{}} 2023-12-27 00:45:53 ollama | {"timestamp":1703666753,"level":"INFO","function":"log_server_request","line":2608,"message":"request","remote_addr":"127.0.0.1","remote_port":43202,"status":200,"method":"POST","path":"/tokenize","params":{}} 2023-12-27 00:45:53 ollama | [GIN] 2023/12/27 - 08:45:53 | 200 | 3.096371564s | 172.20.0.3 | POST "/api/generate" 2023-12-27 00:45:53 ollama-webui | generate ```
GiteaMirror commented 2026-05-20 17:02:09 -05:00
Author
Owner
Copy Link
Copy Source

@tjbck commented on GitHub (Dec 27, 2023):

Hi! Were you using JSON mode? Seems like it's rendering the message it should, could you elaborate more on what exactly is the issue. Thanks!

<!-- gh-comment-id:1870087760 --> @tjbck commented on GitHub (Dec 27, 2023): Hi! Were you using JSON mode? Seems like it's rendering the message it should, could you elaborate more on what exactly is the issue. Thanks!
GiteaMirror commented 2026-05-20 17:02:10 -05:00
Author
Owner
Copy Link
Copy Source

@iukea1 commented on GitHub (Dec 27, 2023):

Hi! Were you using JSON mode? Seems like it's rendering the message it should, could you elaborate more on what exactly is the issue. Thanks!

I believe I was. I will be trying again here in about an hour. Will have more details then

<!-- gh-comment-id:1870147956 --> @iukea1 commented on GitHub (Dec 27, 2023): > Hi! Were you using JSON mode? Seems like it's rendering the message it should, could you elaborate more on what exactly is the issue. Thanks! I believe I was. I will be trying again here in about an hour. Will have more details then
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#115332