llama-cpp-python : Install2024/02/16 |
Install the Python binding [llama-cpp-python] for [llama.cpp], taht is the interface for Meta's Llama (Large Language Model Meta AI) model. |
|
[1] | |
[2] | Install other required packages. |
root@dlp:~# apt -y install python3-pip python3-dev python3-venv gcc g++ make jq |
[3] | Login as a common user and prepare Python virtual environment to install [llama-cpp-python]. |
ubuntu@dlp:~$ python3 -m venv --system-site-packages ~/llama ubuntu@dlp:~$ source ~/llama/bin/activate (llama) ubuntu@dlp:~$ |
[4] | Install [llama-cpp-python]. |
(llama) ubuntu@dlp:~$ pip3 install llama-cpp-python[server] Collecting llama-cpp-python[server] Downloading llama_cpp_python-0.2.44.tar.gz (36.6 MB) Installing build dependencies ... done Getting requirements to build wheel ... done Installing backend dependencies ... done Preparing metadata (pyproject.toml) ... done ..... ..... Successfully installed annotated-types-0.6.0 anyio-4.2.0 diskcache-5.6.3 exceptiongroup-1.2.0 fastapi-0.109.2 h11-0.14.0 llama-cpp-python-0.2.44 numpy-1.26.4 pydantic-2.6.1 pydantic-core-2.16.2 pydantic-settings-2.1.0 python-dotenv-1.0.1 sniffio-1.3.0 sse-starlette-2.0.0 starlette-0.36.3 starlette-context-0.3.6 typing-extensions-4.9.0 uvicorn-0.27.1 |
[5] |
Download the GGUF format model that it can use them in [llama.cpp] and start [llama-cpp-python]. ⇒ https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/tree/main ⇒ https://huggingface.co/TheBloke/Llama-2-70B-Chat-GGUF/tree/main |
(llama) ubuntu@dlp:~$
(llama) ubuntu@dlp:~$ wget https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF/resolve/main/llama-2-13b-chat.Q4_K_M.gguf python3 -m llama_cpp.server --model ./llama-2-13b-chat.Q4_K_M.gguf --host 0.0.0.0 --port 8000 & llama_model_loader: loaded meta data with 19 key-value pairs and 363 tensors from ./llama-2-13b-chat.Q4_K_M.gguf (version GGUF V2) 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 v2 llama_model_loader: - kv 2: llama.context_length u32 = 4096 llama_model_loader: - kv 3: llama.embedding_length u32 = 5120 llama_model_loader: - kv 4: llama.block_count u32 = 40 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 13824 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 40 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 40 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: general.file_type u32 = 15 llama_model_loader: - kv 11: tokenizer.ggml.model str = llama llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 18: general.quantization_version u32 = 2 llama_model_loader: - type f32: 81 tensors llama_model_loader: - type q4_K: 241 tensors llama_model_loader: - type q6_K: 41 tensors llm_load_vocab: special tokens definition check successful ( 259/32000 ). llm_load_print_meta: format = GGUF V2 llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 32000 llm_load_print_meta: n_merges = 0 llm_load_print_meta: n_ctx_train = 4096 llm_load_print_meta: n_embd = 5120 llm_load_print_meta: n_head = 40 llm_load_print_meta: n_head_kv = 40 llm_load_print_meta: n_layer = 40 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 = 1 llm_load_print_meta: n_embd_k_gqa = 5120 llm_load_print_meta: n_embd_v_gqa = 5120 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: n_ff = 13824 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 4096 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: model type = 13B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 13.02 B llm_load_print_meta: model size = 7.33 GiB (4.83 BPW) llm_load_print_meta: general.name = LLaMA v2 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: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.14 MiB llm_load_tensors: CPU buffer size = 7500.85 MiB ..........................warning: failed to mlock 58060800-byte buffer (after previously locking 2057080832 bytes): Cannot allocate memory Try increasing RLIMIT_MEMLOCK ('ulimit -l' as root). .......................................................................... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 1600.00 MiB llama_new_context_with_model: KV self size = 1600.00 MiB, K (f16): 800.00 MiB, V (f16): 800.00 MiB llama_new_context_with_model: CPU input buffer size = 15.01 MiB llama_new_context_with_model: CPU compute buffer size = 200.00 MiB llama_new_context_with_model: graph splits (measure): 1 AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | Model metadata: {'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.architecture': 'llama', 'llama.context_length': '4096', 'general.name': 'LLaMA v2', 'llama.embedding_length': '5120', 'llama.feed_forward_length': '13824', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.dimension_count': '128', 'llama.attention.head_count': '40', 'tokenizer.ggml.bos_token_id': '1', 'llama.block_count': '40', 'llama.attention.head_count_kv': '40', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '15'} INFO: Started server process [2933] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit) |
[6] | You can read the documentation by accessing [http://(server hostname or IP address):8000/docs] from any computer in your local network. |
[7] | Post some questions like follows and verify it works normally. The response time and response contents will vary depending on the question and the model used. However, the response time will take some time because it is executed only on the CPU. By the way, this example is running on a machine with 8 vCPU + 16G memory. |
(llama) ubuntu@dlp:~$ curl -s -XPOST -H 'Content-Type: application/json' localhost:8000/v1/chat/completions \ -d '{"messages": [{"role": "user", "content": "Who are you?"}]}' | jq llama_print_timings: load time = 1926.79 ms llama_print_timings: sample time = 16.65 ms / 76 runs ( 0.22 ms per token, 4564.29 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 = 22648.86 ms / 76 runs ( 298.01 ms per token, 3.36 tokens per second) llama_print_timings: total time = 22809.91 ms / 77 tokens INFO: 127.0.0.1:43678 - "POST /v1/chat/completions HTTP/1.1" 200 OK { "id": "chatcmpl-dccf551d-f0be-4449-835f-8bdc8c1a036d", "object": "chat.completion", "created": 1708061706, "model": "./llama-2-13b-chat.Q4_K_M.gguf", "choices": [ { "index": 0, "message": { "content": " Hello! My name is LLaMA, I'm an AI trained by a team of researcher at Meta AI. My primary function is to assist with tasks and answer questions to the best of my ability. I am capable of understanding and responding to human input in a conversational manner. Please let me know how I can be of assistance today!", "role": "assistant" }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 15, "completion_tokens": 75, "total_tokens": 90 } }(llama) ubuntu@dlp:~$ curl -s -XPOST -H 'Content-Type: application/json' localhost:8000/v1/chat/completions \ -d '{"messages": [{"role": "user", "content": "Tell me about Hiroshima city, Japan."}]}' | jq | sed -e 's/\\n/\n/g' llama_print_timings: load time = 1926.79 ms llama_print_timings: sample time = 114.43 ms / 526 runs ( 0.22 ms per token, 4596.58 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 = 156558.75 ms / 526 runs ( 297.64 ms per token, 3.36 tokens per second) llama_print_timings: total time = 157927.03 ms / 527 tokens INFO: 127.0.0.1:34374 - "POST /v1/chat/completions HTTP/1.1" 200 OK { "id": "chatcmpl-662e47ec-5617-4809-b639-f111d3c04a55", "object": "chat.completion", "created": 1708062685, "model": "./llama-2-13b-chat.Q4_K_M.gguf", "choices": [ { "index": 0, "message": { "content": " Sure, I'd be happy to tell you about Hiroshima City, Japan! Hiroshima is a city located in the Chugoku region of western Japan. It is best known for being the first city in the world to be targeted by an atomic bomb when it was dropped by the United States on August 6, 1945, during the final stages of World War II. The bombing killed an estimated 70,000 people instantly, and another 70,000 died from injuries and radiation sickness in the months and years that followed. Today, Hiroshima is a thriving city with a population of over 1 million people. The Hiroshima Peace Memorial Park, which includes the Atomic Bomb Dome (the ruins of the prefectural headquarters building that survived the blast), the Children's Peace Monument, and the Memorial Museum, serves as a reminder of the devastating effects of nuclear weapons and the importance of promoting peace and disarmament. The park was dedicated to the memory of the victims of the atomic bombing and as a symbol of hope for peace and nuclear disarmament. In addition to its historical significance, Hiroshima is also known for its traditional cuisine, which includes dishes such as okonomiyaki (a savory pancake made with batter, vegetables, and meat) and oysters, as well as its festivals and cultural events, such as the Hiroshima Festival, which takes place in August and features traditional music and dance performances, and the Hiroshima Animation Festival, which showcases the work of animators from around the world. The city also has several notable landmarks and attractions, including the Hiroshima Castle, which was built in the 16th century and has been reconstructed several times after being destroyed by wars and natural disasters; the Miyajima Island, which is famous for its beautiful scenery and historic landmarks such as the famous Itsukushima Shrine, which appears to be floating on water during high tide; and the Hiroshima Museum of Art, which features a collection of modern and contemporary art from Japanese and international artists. Overall, Hiroshima is a city with a rich history and culture, and it continues to play an important role in promoting peace and disarmament around the world.", "role": "assistant" }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 23, "completion_tokens": 525, "total_tokens": 548 } } |
|