Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| llama-ko-peft-v0.5.Q2_K.gguf | Q2_K | 2.42GB |
| llama-ko-peft-v0.5.Q3_K_S.gguf | Q3_K_S | 2.81GB |
| llama-ko-peft-v0.5.Q3_K.gguf | Q3_K | 3.14GB |
| llama-ko-peft-v0.5.Q3_K_M.gguf | Q3_K_M | 3.14GB |
| llama-ko-peft-v0.5.Q3_K_L.gguf | Q3_K_L | 3.42GB |
| llama-ko-peft-v0.5.IQ4_XS.gguf | IQ4_XS | 3.47GB |
| llama-ko-peft-v0.5.Q4_0.gguf | Q4_0 | 3.64GB |
| llama-ko-peft-v0.5.IQ4_NL.gguf | IQ4_NL | 3.66GB |
| llama-ko-peft-v0.5.Q4_K_S.gguf | Q4_K_S | 3.67GB |
| llama-ko-peft-v0.5.Q4_K.gguf | Q4_K | 3.88GB |
| llama-ko-peft-v0.5.Q4_K_M.gguf | Q4_K_M | 3.88GB |
| llama-ko-peft-v0.5.Q4_1.gguf | Q4_1 | 4.03GB |
| llama-ko-peft-v0.5.Q5_0.gguf | Q5_0 | 4.42GB |
| llama-ko-peft-v0.5.Q5_K_S.gguf | Q5_K_S | 4.42GB |
| llama-ko-peft-v0.5.Q5_K.gguf | Q5_K | 4.54GB |
| llama-ko-peft-v0.5.Q5_K_M.gguf | Q5_K_M | 4.54GB |
| llama-ko-peft-v0.5.Q5_1.gguf | Q5_1 | 4.8GB |
| llama-ko-peft-v0.5.Q6_K.gguf | Q6_K | 5.24GB |
| llama-ko-peft-v0.5.Q8_0.gguf | Q8_0 | 6.79GB |
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
## v2 models
model_path = "colable/llama-ko-peft-v0.5"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")