You can deploy this model and start earning money today!

RichardErkhov/
VIRNECT_-_llama-3-Korean-8B-r-v1-gguf

Name: VIRNECT_-_llama-3-Korean-8B-r-v1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-Korean-8B-r-v1 - GGUF

Model creator: https://huggingface.co/VIRNECT/
Original model: https://huggingface.co/VIRNECT/llama-3-Korean-8B-r-v1/

Name	Quant method	Size
llama-3-Korean-8B-r-v1.Q2_K.gguf	Q2_K	2.96GB
llama-3-Korean-8B-r-v1.IQ3_XS.gguf	IQ3_XS	3.28GB
llama-3-Korean-8B-r-v1.IQ3_S.gguf	IQ3_S	3.43GB
llama-3-Korean-8B-r-v1.Q3_K_S.gguf	Q3_K_S	3.41GB
llama-3-Korean-8B-r-v1.IQ3_M.gguf	IQ3_M	3.52GB
llama-3-Korean-8B-r-v1.Q3_K.gguf	Q3_K	3.74GB
llama-3-Korean-8B-r-v1.Q3_K_M.gguf	Q3_K_M	3.74GB
llama-3-Korean-8B-r-v1.Q3_K_L.gguf	Q3_K_L	4.03GB
llama-3-Korean-8B-r-v1.IQ4_XS.gguf	IQ4_XS	4.18GB
llama-3-Korean-8B-r-v1.Q4_0.gguf	Q4_0	4.34GB
llama-3-Korean-8B-r-v1.IQ4_NL.gguf	IQ4_NL	4.38GB
llama-3-Korean-8B-r-v1.Q4_K_S.gguf	Q4_K_S	4.37GB
llama-3-Korean-8B-r-v1.Q4_K.gguf	Q4_K	4.58GB
llama-3-Korean-8B-r-v1.Q4_K_M.gguf	Q4_K_M	4.58GB
llama-3-Korean-8B-r-v1.Q4_1.gguf	Q4_1	4.78GB
llama-3-Korean-8B-r-v1.Q5_0.gguf	Q5_0	5.21GB
llama-3-Korean-8B-r-v1.Q5_K_S.gguf	Q5_K_S	5.21GB
llama-3-Korean-8B-r-v1.Q5_K.gguf	Q5_K	5.34GB
llama-3-Korean-8B-r-v1.Q5_K_M.gguf	Q5_K_M	5.34GB
llama-3-Korean-8B-r-v1.Q5_1.gguf	Q5_1	5.65GB
llama-3-Korean-8B-r-v1.Q6_K.gguf	Q6_K	6.14GB
llama-3-Korean-8B-r-v1.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 language:

ko
en library_name: transformers pipeline_tag: text-generation

Python code with Pipeline

python

import transformers
import torch

model_id = "VIRNECT/llama-3-Korean-8B-r-v1"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

pipeline.model.eval()

PROMPT = '''You are a helpful AI assistant. Please answer the user's questions kindly. 당신은 유능한 AI 어시스턴트 입니다. 사용자의 질문에 대해 친절하게 답변해주세요.'''
instruction = "화학공학이 다른 공학 분야와 어떻게 다른가요?"

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)

print(outputs[0]["generated_text"][len(prompt):])

RichardErkhov/VIRNECT_-_llama-3-Korean-8B-r-v1-gguf

Original model description:

Python code with Pipeline

RichardErkhov/
VIRNECT_-_llama-3-Korean-8B-r-v1-gguf