Downloads · 30 days
87
6% of all-time downloads
RichardErkhov/VIRNECT_-_llama-3-Korean-8B-V2-gguf
VIRNECT_-_llama-3-Korean-8B-V2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
87
6% of all-time downloads
All-time downloads
1.5K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama-3-Korean-8B-V2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| llama-3-Korean-8B-V2.Q2_K.gguf | Q2_K | 2.96GB |
| llama-3-Korean-8B-V2.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| llama-3-Korean-8B-V2.IQ3_S.gguf | IQ3_S | 3.43GB |
| llama-3-Korean-8B-V2.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| llama-3-Korean-8B-V2.IQ3_M.gguf | IQ3_M | 3.52GB |
| llama-3-Korean-8B-V2.Q3_K.gguf | Q3_K | 3.74GB |
| llama-3-Korean-8B-V2.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| llama-3-Korean-8B-V2.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| llama-3-Korean-8B-V2.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| llama-3-Korean-8B-V2.Q4_0.gguf | Q4_0 | 4.34GB |
| llama-3-Korean-8B-V2.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| llama-3-Korean-8B-V2.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| llama-3-Korean-8B-V2.Q4_K.gguf | Q4_K | 4.58GB |
| llama-3-Korean-8B-V2.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| llama-3-Korean-8B-V2.Q4_1.gguf | Q4_1 | 4.78GB |
| llama-3-Korean-8B-V2.Q5_0.gguf | Q5_0 | 5.21GB |
| llama-3-Korean-8B-V2.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| llama-3-Korean-8B-V2.Q5_K.gguf | Q5_K | 5.34GB |
| llama-3-Korean-8B-V2.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| llama-3-Korean-8B-V2.Q5_1.gguf | Q5_1 | 5.65GB |
| llama-3-Korean-8B-V2.Q6_K.gguf | Q6_K | 6.14GB |
| llama-3-Korean-8B-V2.Q8_0.gguf | Q8_0 | 7.95GB |
license: llama3 language:
import transformers
import torch
model_id = "VIRNECT/llama-3-Korean-8B-V2"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
pipeline.model.eval()
PROMPT = '''당신은 인간과 대화하는 친절한 챗봇입니다. 질문에 대한 정보를 상황에 맞게 자세히 제공합니다. 당신이 질문에 대한 답을 모른다면, 사실은 모른다고 말합니다.'''
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):])