Yes I believe that means rebar is disabled. I read somewhere that 10 series nvidia cards dont even support rebar but i did find this: GitHub - terminatorul/NvStrapsReBar: Resizable BAR for Turring GTX 1600 / RTX 2000 GPUs over my head though.
Here are the logs:
==========
== CUDA ==
==========
CUDA Version 12.0.0
Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.
*************************
** DEPRECATION NOTICE! **
*************************
THIS IMAGE IS DEPRECATED and is scheduled for DELETION.
https://gitlab.com/nvidia/container-images/cuda/blob/master/doc/support-policy.md
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
llama_model_loader: loaded meta data with 25 key-value pairs and 291 tensors from /root/.cache/huggingface/hub/models--meetkai--functionary-small-v2.4-GGUF/snapshots/a0d171eb78e02a58858c464e278234afbcf85c5c/./functionary-small-v2.4.Q4_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.name str = .
llama_model_loader: - kv 2: llama.vocab_size u32 = 32004
llama_model_loader: - kv 3: llama.context_length u32 = 32768
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.block_count u32 = 32
llama_model_loader: - kv 6: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 7: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 10: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 11: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 12: general.file_type u32 = 2
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,32004] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,32004] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,32004] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.ggml.padding_token_id u32 = 2
llama_model_loader: - kv 21: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 22: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 23: tokenizer.chat_template str = {% for message in messages %}\n{% if m...
llama_model_loader: - kv 24: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 263/32004 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32004
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
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 = 14336
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
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 = linear
llm_load_print_meta: freq_base_train = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 32768
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: model type = 8B
llm_load_print_meta: model ftype = Q4_0
llm_load_print_meta: model params = 7.24 B
llm_load_print_meta: model size = 3.83 GiB (4.54 BPW)
llm_load_print_meta: general.name = .
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 2 '</s>'
llm_load_print_meta: LF token = 13 '<0x0A>'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce GTX 1080, compute capability 6.1, VMM: yes
llm_load_tensors: ggml ctx size = 0.30 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: CPU buffer size = 70.32 MiB
llm_load_tensors: CUDA0 buffer size = 3847.57 MiB
..................................................................................................
llama_new_context_with_model: n_ctx = 8000
llama_new_context_with_model: n_batch = 192
llama_new_context_with_model: n_ubatch = 192
llama_new_context_with_model: freq_base = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 1000.00 MiB
llama_new_context_with_model: KV self size = 1000.00 MiB, K (f16): 500.00 MiB, V (f16): 500.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.14 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 205.36 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 8.86 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 2
AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 |
Model metadata: {'tokenizer.chat_template': '{% for message in messages %}\n{% if message[\'role\'] == \'user\' or message[\'role\'] == \'system\' %}\n{{ \'<|from|>\' + message[\'role\'] + \'\n<|recipient|>all\n<|content|>\' + message[\'content\'] + \'\n\' }}{% elif message[\'role\'] == \'tool\' %}\n{{ \'<|from|>\' + message[\'name\'] + \'\n<|recipient|>all\n<|content|>\' + message[\'content\'] + \'\n\' }}{% else %}\n{% set contain_content=\'no\'%}\n{% if message[\'content\'] is not none %}\n{{ \'<|from|>assistant\n<|recipient|>all\n<|content|>\' + message[\'content\'] }}{% set contain_content=\'yes\'%}\n{% endif %}\n{% if \'tool_calls\' in message and message[\'tool_calls\'] is not none %}\n{% for tool_call in message[\'tool_calls\'] %}\n{% set prompt=\'<|from|>assistant\n<|recipient|>\' + tool_call[\'function\'][\'name\'] + \'\n<|content|>\' + tool_call[\'function\'][\'arguments\'] %}\n{% if loop.index == 1 and contain_content == "no" %}\n{{ prompt }}{% else %}\n{{ \'\n\' + prompt}}{% endif %}\n{% endfor %}\n{% endif %}\n{{ \'<|stop|>\n\' }}{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ \'<|from|>assistant\n<|recipient|>\' }}{% endif %}', 'tokenizer.ggml.add_eos_token': 'false', 'tokenizer.ggml.padding_token_id': '2', 'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.architecture': 'llama', 'llama.rope.freq_base': '1000000.000000', 'llama.context_length': '32768', 'general.name': '.', 'llama.vocab_size': '32004', 'general.file_type': '2', 'tokenizer.ggml.add_bos_token': 'true', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.dimension_count': '128', 'tokenizer.ggml.bos_token_id': '1', 'llama.attention.head_count': '32', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8'}
INFO: Started server process [27]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 1.14 ms / 3 runs ( 0.38 ms per token, 2638.52 tokens per second)
llama_print_timings: prompt eval time = 9973.59 ms / 4515 tokens ( 2.21 ms per token, 452.70 tokens per second)
llama_print_timings: eval time = 83.80 ms / 2 runs ( 41.90 ms per token, 23.87 tokens per second)
llama_print_timings: total time = 19062.25 ms / 4517 tokens
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 20.23 ms / 51 runs ( 0.40 ms per token, 2520.76 tokens per second)
llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second)
llama_print_timings: eval time = 2139.32 ms / 51 runs ( 41.95 ms per token, 23.84 tokens per second)
llama_print_timings: total time = 4057.04 ms / 52 tokens
INFO: 192.168.1.68:52060 - "POST /v1/chat/completions HTTP/1.1" 200 OK
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 1.18 ms / 3 runs ( 0.39 ms per token, 2542.37 tokens per second)
llama_print_timings: prompt eval time = 8125.97 ms / 3788 tokens ( 2.15 ms per token, 466.16 tokens per second)
llama_print_timings: eval time = 83.89 ms / 2 runs ( 41.95 ms per token, 23.84 tokens per second)
llama_print_timings: total time = 15740.95 ms / 3790 tokens
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 1.50 ms / 4 runs ( 0.37 ms per token, 2670.23 tokens per second)
llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second)
llama_print_timings: eval time = 167.80 ms / 4 runs ( 41.95 ms per token, 23.84 tokens per second)
llama_print_timings: total time = 323.15 ms / 5 tokens
INFO: 192.168.1.68:39282 - "POST /v1/chat/completions HTTP/1.1" 200 OK
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 1.94 ms / 5 runs ( 0.39 ms per token, 2573.34 tokens per second)
llama_print_timings: prompt eval time = 8178.00 ms / 3787 tokens ( 2.16 ms per token, 463.07 tokens per second)
llama_print_timings: eval time = 168.47 ms / 4 runs ( 42.12 ms per token, 23.74 tokens per second)
llama_print_timings: total time = 15947.85 ms / 3791 tokens
from_string grammar:
char ::= [^"\] | [\] char_1
char_1 ::= ["\/bfnrt] | [u] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]
list ::= [[] space list_8 []] space
space ::= space_19
list_4 ::= list-item list_7
list-item ::= [{] space list-item-domain-kv [,] space list-item-service-kv [,] space list-item-service-data-kv [}] space
list_6 ::= [,] space list-item
list_7 ::= list_6 list_7 |
list_8 ::= list_4 |
list-item-domain-kv ::= ["] [d] [o] [m] [a] [i] [n] ["] space [:] space string
list-item-service-kv ::= ["] [s] [e] [r] [v] [i] [c] [e] ["] space [:] space string
list-item-service-data-kv ::= ["] [s] [e] [r] [v] [i] [c] [e] [_] [d] [a] [t] [a] ["] space [:] space list-item-service-data
string ::= ["] string_20 ["] space
list-item-service-data ::= [{] space list-item-service-data-entity-id-kv [}] space
list-item-service-data-entity-id-kv ::= ["] [e] [n] [t] [i] [t] [y] [_] [i] [d] ["] space [:] space string
list-kv ::= ["] [l] [i] [s] [t] ["] space [:] space list
root ::= [{] space root_18 [}] space
root_17 ::= list-kv
root_18 ::= root_17 |
space_19 ::= [ ] |
string_20 ::= char string_20 |
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
list ::= "[" space (list-item ("," space list-item)*)? "]" space
list-item ::= "{" space list-item-domain-kv "," space list-item-service-kv "," space list-item-service-data-kv "}" space
list-item-domain-kv ::= "\"domain\"" space ":" space string
list-item-service-data ::= "{" space list-item-service-data-entity-id-kv "}" space
list-item-service-data-entity-id-kv ::= "\"entity_id\"" space ":" space string
list-item-service-data-kv ::= "\"service_data\"" space ":" space list-item-service-data
list-item-service-kv ::= "\"service\"" space ":" space string
list-kv ::= "\"list\"" space ":" space list
root ::= "{" space (list-kv )? "}" space
space ::= " "?
string ::= "\"" char* "\"" space
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 238.41 ms / 39 runs ( 6.11 ms per token, 163.58 tokens per second)
llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second)
llama_print_timings: eval time = 1638.57 ms / 39 runs ( 42.01 ms per token, 23.80 tokens per second)
llama_print_timings: total time = 3358.07 ms / 40 tokens
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 0.37 ms / 1 runs ( 0.37 ms per token, 2702.70 tokens per second)
llama_print_timings: prompt eval time = 248.64 ms / 38 tokens ( 6.54 ms per token, 152.83 tokens per second)
llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_print_timings: total time = 361.24 ms / 39 tokens
INFO: 192.168.1.68:57354 - "POST /v1/chat/completions HTTP/1.1" 200 OK
Llama.generate: prefix-match hit
llama_print_timings: load time = 1098.02 ms
llama_print_timings: sample time = 3.69 ms / 10 runs ( 0.37 ms per token, 2707.09 tokens per second)
llama_print_timings: prompt eval time = 181.49 ms / 10 tokens ( 18.15 ms per token, 55.10 tokens per second)
llama_print_timings: eval time = 379.00 ms / 9 runs ( 42.11 ms per token, 23.75 tokens per second)
llama_print_timings: total time = 963.92 ms / 19 tokens
INFO: 192.168.1.68:57354 - "POST /v1/chat/completions HTTP/1.1" 200 OK
simple question took 16seconds. func call to turn on some lights took 23.
System prompt is:
I want you to act as smart home manager of Home Assistant.
I will provide information of smart home along with a question, you will truthfully make correction or answer using information provided in one sentence in everyday language.
Current Time: {{now()}}
Available Devices:
```csv
entity_id,name,state,aliases
{% for entity in exposed_entities -%}
{{ entity.entity_id }},{{ entity.name }},{{ entity.state }},{{entity.aliases | join('/')}}
{% endfor -%}
The current state of devices is provided in available devices.
Use execute_services function only for requested action, not for current states.
Do not execute service without user's confirmation.
Do not restate or appreciate what user says, rather make a quick inquiry.
