Edit model card

Gugugo-koen-7B-V1.1

Detail repo: https://github.com/jwj7140/Gugugo Gugugo

Base Model: Llama-2-ko-7b

Training Dataset: sharegpt_deepl_ko_translation.

I trained with 1x A6000 GPUs for 90 hours.

Prompt Template

KO->EN

### ํ•œ๊ตญ์–ด: {sentence}</๋>
### ์˜์–ด:

EN->KO

### ์˜์–ด: {sentence}</๋>
### ํ•œ๊ตญ์–ด:

Implementation Code

from vllm import LLM, SamplingParams

def make_prompt(data):
    prompts = []
    for line in data:
        prompts.append(f"### ์˜์–ด: {line}</๋>\n### ํ•œ๊ตญ์–ด:")
    return prompts

texts = [
  "Hello world!",
  "Nice to meet you!"
]

prompts = make_prompt(texts)

sampling_params = SamplingParams(temperature=0.01, stop=["</๋>"], max_tokens=700)

llm = LLM(model="squarelike/Gugugo-koen-7B-V1.1-AWQ", quantization="awq", dtype="half")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    print(output.outputs[0].text)
Downloads last month
5
Safetensors
Model size
1.25B params
Tensor type
I32
ยท
FP16
ยท

Dataset used to train squarelike/Gugugo-koen-7B-V1.1-AWQ