You can deploy this model and start earning money today!

RichardErkhov/
CarrotAI_-_ko-gemma-2b-it-sft-gguf

Name: CarrotAI_-_ko-gemma-2b-it-sft-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ko-gemma-2b-it-sft - GGUF

Model creator: https://huggingface.co/CarrotAI/
Original model: https://huggingface.co/CarrotAI/ko-gemma-2b-it-sft/

Name	Quant method	Size
ko-gemma-2b-it-sft.Q2_K.gguf	Q2_K	1.08GB
ko-gemma-2b-it-sft.IQ3_XS.gguf	IQ3_XS	1.16GB
ko-gemma-2b-it-sft.IQ3_S.gguf	IQ3_S	1.2GB
ko-gemma-2b-it-sft.Q3_K_S.gguf	Q3_K_S	1.2GB
ko-gemma-2b-it-sft.IQ3_M.gguf	IQ3_M	1.22GB
ko-gemma-2b-it-sft.Q3_K.gguf	Q3_K	1.29GB
ko-gemma-2b-it-sft.Q3_K_M.gguf	Q3_K_M	1.29GB
ko-gemma-2b-it-sft.Q3_K_L.gguf	Q3_K_L	1.36GB
ko-gemma-2b-it-sft.IQ4_XS.gguf	IQ4_XS	1.4GB
ko-gemma-2b-it-sft.Q4_0.gguf	Q4_0	1.44GB
ko-gemma-2b-it-sft.IQ4_NL.gguf	IQ4_NL	1.45GB
ko-gemma-2b-it-sft.Q4_K_S.gguf	Q4_K_S	1.45GB
ko-gemma-2b-it-sft.Q4_K.gguf	Q4_K	1.52GB
ko-gemma-2b-it-sft.Q4_K_M.gguf	Q4_K_M	1.52GB
ko-gemma-2b-it-sft.Q4_1.gguf	Q4_1	1.56GB
ko-gemma-2b-it-sft.Q5_0.gguf	Q5_0	1.68GB
ko-gemma-2b-it-sft.Q5_K_S.gguf	Q5_K_S	1.68GB
ko-gemma-2b-it-sft.Q5_K.gguf	Q5_K	1.71GB
ko-gemma-2b-it-sft.Q5_K_M.gguf	Q5_K_M	1.71GB
ko-gemma-2b-it-sft.Q5_1.gguf	Q5_1	1.79GB
ko-gemma-2b-it-sft.Q6_K.gguf	Q6_K	1.92GB
ko-gemma-2b-it-sft.Q8_0.gguf	Q8_0	2.49GB

Original model description:

language:

ko
en library_name: transformers datasets:
nlpai-lab/kullm-v2

Model

Model Page: Gemma

fine-tuned the google/gemma-2b-it model.

How to Use it

python

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("carrotter/ko-gemma-2b-it-sft")
model = AutoModelForCausalLM.from_pretrained("carrotter/ko-gemma-2b-it-sft")

chat = [
    { "role": "user", "content": "피보나치 수열 파이썬 코드로 알려줘" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=100)
print(tokenizer.decode(outputs[0]))

Example Output

python

<bos><start_of_turn>user
피보나치 수열 파이썬 코드로 알려줘<end_of_turn>
<start_of_turn>model
다음은 피보나치 수열을 파이썬으로 구현하는 방법의 예입니다:

def fibonacci(n):
    if n <= 1:
        return n
    else:
        return fibonacci(n-1) + fibonacci(n-2)

이 함수는 n이 피보나치 수열의 몇 번째 항인지에 따라 반환합니다. n이 1이거나 2인 경우

Applications

This fine-tuned model is particularly suited for [mention applications, e.g., chatbots, question-answering systems, etc.]. Its enhanced capabilities ensure more accurate and contextually appropriate responses in these domains.

Limitations and Considerations

While our fine-tuning process has optimized the model for specific tasks, it's important to acknowledge potential limitations. The model's performance can still vary based on the complexity of the task and the specificities of the input data. Users are encouraged to evaluate the model thoroughly in their specific context to ensure it meets their requirements.

RichardErkhov/CarrotAI_-_ko-gemma-2b-it-sft-gguf