C2LLM-0.5B

from transformers import AutoModel, AutoTokenizer
import torch

model_path = "codefuse-ai/C2LLM-0.5B"

# Load the model
model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16, trust_remote_code=True)

# Prepare your custom instruction
instruction = "xxxxx"

# Prepare the data
sentences = ['''int r = (int) params >> 8 & 0xff;
int p = (int) params & 0xff;

byte[] derived1 = SCrypt.scrypt(passwd.getBytes("UTF-8"), salt, N, r, p, 32);

if (derived0.length != derived1.length) return false;

int result = 0;
for (int i = 0; i < derived0.length; i++) {
result |= derived0[i] ^ derived1[i];
}
return result == 0;
} catch (UnsupportedEncodingException e) {
throw new IllegalStateException("JVM doesn't support UTF-8?");
} catch (GeneralSecurityException e) {
throw new IllegalStateException("JVM doesn't support SHA1PRNG or HMAC_SHA256?");
}
}''',
'''	
}
if (tempFrom > tempTo) {
return new RangeInfo(inclusive ? tempTo : tempTo + 1, tempFrom + 1, true);
}
return new RangeInfo(tempFrom, inclusive ? tempTo + 1 : tempTo, false);
}''']

sentences = [instruction+sentence for sentence in sentences]

# Get the embeddings
embeddings = model.encode(sentences)

from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer("codefuse-ai/C2LLM-0.5B", trust_remote_code=True, tokenizer_kwargs={"padding_side":"left"})

# Prepare your custom instruction
instruction = "xxxxx"

# Prepare the data
sentences = ['''int r = (int) params >> 8 & 0xff;
int p = (int) params & 0xff;

byte[] derived1 = SCrypt.scrypt(passwd.getBytes("UTF-8"), salt, N, r, p, 32);

if (derived0.length != derived1.length) return false;

int result = 0;
for (int i = 0; i < derived0.length; i++) {
result |= derived0[i] ^ derived1[i];
}
return result == 0;
} catch (UnsupportedEncodingException e) {
throw new IllegalStateException("JVM doesn't support UTF-8?");
} catch (GeneralSecurityException e) {
throw new IllegalStateException("JVM doesn't support SHA1PRNG or HMAC_SHA256?");
}
}''',
'''	
}
if (tempFrom > tempTo) {
return new RangeInfo(inclusive ? tempTo : tempTo + 1, tempFrom + 1, true);
}
return new RangeInfo(tempFrom, inclusive ? tempTo + 1 : tempTo, false);
}''']

sentences = [instruction+sentence for sentence in sentences]

# Get the embeddings
embeddings = model.encode(sentences)