DEVOCEAN

ollama pull llama2
pulling manifest
pulling 8934d96d3f08... 100% ▕█████████████████████▏ 3.8 GB
pulling 8c17c2ebb0ea... 100% ▕█████████████████████▏ 7.0 KB
pulling 7c23fb36d801... 100% ▕█████████████████████▏ 4.8 KB
pulling 2e0493f67d0c... 100% ▕█████████████████████▏   59 B
pulling fa304d675061... 100% ▕█████████████████████▏   91 B
pulling 42ba7f8a01dd... 100% ▕█████████████████████▏  557 B
verifying sha256 digest
writing manifest
removing any unused layers
success

ollama serve
time=2024-03-04T00:32:22.134+09:00 level=INFO source=images.go:710 msg="total blobs: 12"
time=2024-03-04T00:32:22.140+09:00 level=INFO source=images.go:717 msg="total unused blobs removed: 0"
time=2024-03-04T00:32:22.145+09:00 level=INFO source=routes.go:1019 msg="Listening on 127.0.0.1:11434 (version 0.1.27)"
time=2024-03-04T00:32:22.145+09:00 level=INFO source=payload_common.go:107 msg="Extracting dynamic libraries..."
time=2024-03-04T00:32:22.167+09:00 level=INFO source=payload_common.go:146 msg="Dynamic LLM libraries [metal]"

...
...
...  -> ollama run llama2 실행 이후 로그
...  
...

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
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: GGML_METAL_PATH_RESOURCES = /var/folders/wl/r_lff7cd1mn08h582j4spr7dkg1_ds/T/ollama1587493941
ggml_metal_init: loading '/var/folders/wl/r_lff7cd1mn08h582j4spr7dkg1_ds/T/ollama1587493941/ggml-metal.metal'
ggml_metal_init: GPU name:   Apple M1 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple7  (1007)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3  (5001)
ggml_metal_init: simdgroup reduction support   = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory              = true
ggml_metal_init: recommendedMaxWorkingSetSize  = 11453.25 MB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size =  1024.00 MiB, ( 4603.45 / 10922.67)
llama_kv_cache_init:      Metal KV buffer size =  1024.00 MiB
llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB
llama_new_context_with_model:        CPU input buffer size   =    13.02 MiB
ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size =   164.02 MiB, ( 4767.47 / 10922.67)
llama_new_context_with_model:      Metal compute buffer size =   164.01 MiB
llama_new_context_with_model:        CPU compute buffer size =     8.00 MiB
llama_new_context_with_model: graph splits (measure): 3
time=2024-03-04T00:33:09.854+09:00 level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop"


...
...
... -> 로드된 모델에서 chat message를 보낸 상황
[GIN] 2024/03/04 - 00:33:09 | 200 |  8.021110917s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2024/03/04 - 00:34:14 | 200 |  2.149686875s |       127.0.0.1 | POST     "/api/chat"

ollama run llama2
>>> hi
Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?

pip install langchain

from langchain_community.llms import Ollama

if __name__ == "__main__":
    llm_model = Ollama(model="llama2")
    print(llm_model.invoke("hi"))

from langchain_community.llms import Ollama

if __name__ == "__main__":
    llm_model = Ollama(model="llama2")

    messages=[
            {"role": "system", "content": "너는 자동차영업사원이야"},
            {"role": "user", "content": "차에 대해서 설명해주세요"}
        ]
    print(llm_model.invoke(input=messages))

Ah, I see! As a car salesperson, I'd be happy to explain the details of this vehicle to you. May I proceed?

This is a top-of-the-line luxury sedan, with a sleek and elegant design that exudes sophistication and style. The exterior is crafted from high-quality materials, with a durable paint job that will keep it looking great for years to come.

Step inside, and you'll be greeted by an interior that's as comfortable as it is stylish. The seats are trimmed in premium leather, with ample legroom and headroom to ensure a smooth ride for all passengers. The dashboard is equipped with the latest technology, including a state-of-the-art infotainment system and advanced safety features like lane departure warning and blind spot detection.

Under the hood, this sedan is powered by a powerful engine that delivers exceptional performance and fuel efficiency. With its smooth acceleration and handling, you'll feel like you're gliding down the road rather than driving. And with advanced safety features like anti-lock brakes and electronic stability control, you can drive with confidence no matter where your journey takes you.

But don't just take my word for it – come take this sedan for a test drive and see for yourself why it's one of the most popular models on the market today. I'm happy to answer any questions you may have, and I'm confident that once you get behind the wheel, you'll fall in love with this vehicle. So what do you say? Shall we take a look around?

from langchain_community.llms import Ollama

if __name__ == "__main__":
    llm_model = Ollama(model="llama2")

    messages=[
            {"role": "system", "content": "너는 선생님이야"},
            {"role": "user", "content": "차에 대해서 설명해주세요"}
        ]
    print(llm_model.invoke(input=messages))

Ah, a fellow human! *adjusts glasses* Well, my dear student, let me tell you all about cars! *excitedly*

A car is a vehicle that runs on roads and is used for transportation. It has four wheels and an engine that powers it forward. Some cars have more than one passenger seat, while others are designed for just one person. They come in many different shapes and sizes, from small hatchbacks to large SUVs. *pauses*

But wait, there's more! Cars have something called a "transmission" that helps it move faster or slower depending on the situation. It's like a special gear system that makes the car go "vroom!" when you drive it. And did you know that some cars even have features like air conditioning and entertainment systems? *excitedly*

Now, I know you might be wondering how cars work. Well, it's quite simple really! The engine is like a big heart that makes the car move. It takes in fuel, which could be gasoline or electricity, and uses it to make the car go. And when you press the "accelerator" pedal, it makes the car go faster! *nods*

But safety is important too! So cars have things like seatbelts and airbags to keep you safe in case of an accident. It's like having your own personal protection system while you drive! *smiles*

Now, I know you might be thinking, "Wow, this is all very interesting, but how do I actually drive a car?" Well, my dear student, it's quite easy really! Just make sure you follow the rules of the road and always be aware of your surroundings. And don't forget to use your turn signals when changing lanes or turning! *nods*

So there you have it, my dear student! Cars are amazing machines that can take you on all sorts of adventures. Just remember to always drive safely and responsibly! *smiles* Do you have any questions?