• maywell/Synatra-7B-v0.3-Translation λͺ¨λΈμ΄ ν”„λ‘œκ·Έλž¨ μ½”λ“œκ°€ ν¬ν•¨λœ μ—¬λŸ¬ μ€„μ˜ κΈ΄ ν…μŠ€νŠΈλ₯Ό λ²ˆμ—­ν•˜λŠ”λ° μ œν•œμ΄ μžˆμ–΄μ„œ ν•΄λ‹Ή 뢀뢄을 LoRA둜 μΆ”κ°€ ν•™μŠ΅ν–ˆμŠ΅λ‹ˆλ‹€.

μ‚¬μš© μ˜ˆμ‹œ

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda:0" if torch.cuda.is_available() else "cpu"

model_id = "maywell/Synatra-7B-v0.3-Translation"
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=model_revision)
model = AutoModelForCausalLM.from_pretrained(model_id, revision=model_revision, device_map=device, torch_dtype=torch.float16).eval()

# LoRA μ–΄λŒ‘ν„° 뢈러였기
model.load_adapter("heegyu/Synatra-7B-v0.3-Translation-glaive")


def generate(prompt, *messages):
  messages = [
      {
          "role": "system",
          "content": prompt.strip(),
      },
      *[{"role": "user" if i % 2 == 0 else "assistant", "content": m.strip()} for i, m in enumerate(messages)],
  ]
  inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(device)
  outs = model.generate(inputs, do_sample=True, max_new_tokens=256, early_stopping=True)
  print(tokenizer.batch_decode(outs)[0])

generate(
    "λ§ˆν¬λ‹€μš΄μœΌλ‘œ μž‘μ„±λœ μ˜μ–΄ λŒ€ν™”λ₯Ό ν•œκ΅­μ–΄λ‘œ λ²ˆμ—­ν•˜μ„Έμš”. ν”„λ‘œκ·Έλž¨ μ½”λ“œλŠ” λ²ˆμ—­ν•˜λ©΄ μ•ˆλ©λ‹ˆλ‹€.",
"""
### User:
Given a list ["foo", "bar", "baz"] and an item in the list "bar", how do I get its index 1?

### Assistant:
```python
>>> ["foo", "bar", "baz"].index("bar")
1
```
See the documentation for the built-in .index() method of the list:

list.index(x[, start[, end]])
Return zero-based index in the list of the first item whose value is equal to x. Raises a ValueError if there is no such item.

The optional arguments start and end are interpreted as in the slice notation and are used to limit the search to a particular subsequence of the list. The returned index is computed relative to the beginning of the full sequence rather than the start argument.
"""
)

μ‹€ν–‰ κ²°κ³Ό

<|im_start|> system
λ§ˆν¬λ‹€μš΄μœΌλ‘œ μž‘μ„±λœ μ˜μ–΄ λŒ€ν™”λ₯Ό ν•œκ΅­μ–΄λ‘œ λ²ˆμ—­ν•˜μ„Έμš”. ν”„λ‘œκ·Έλž¨ μ½”λ“œλŠ” λ²ˆμ—­ν•˜λ©΄ μ•ˆλ©λ‹ˆλ‹€.<|im_end|> 
<|im_start|> user
### User:
Given a list ["foo", "bar", "baz"] and an item in the list "bar", how do I get its index 1?

### Assistant:
```python
>>> ["foo", "bar", "baz"].index("bar")
1
```
See the documentation for the built-in .index() method of the list:

list.index(x[, start[, end]])
Return zero-based index in the list of the first item whose value is equal to x. Raises a ValueError if there is no such item.

The optional arguments start and end are interpreted as in the slice notation and are used to limit the search to a particular subsequence of the list. The returned index is computed relative to the beginning of the full sequence rather than the start argument.<|im_end|> 
<|im_start|> assistant
 ### User:
"foo", "bar", "baz" λ¦¬μŠ€νŠΈκ°€ 있고 λ¦¬μŠ€νŠΈμ—μ„œ "bar"λΌλŠ” ν•­λͺ©μ΄ μžˆλ‹€λ©΄, κ·Έ 인덱슀 1을 μ–΄λ–»κ²Œ κ°€μ Έμ˜¬ 수 μžˆμ„κΉŒμš”?

### Assistant:
```python
>>> ["foo", "bar", "baz"].index("bar")
1
```
리슀트의 λ‚΄μž₯된 .index() λ©”μ„œλ“œμ— λŒ€ν•œ λ¬Έμ„œλ₯Ό μ°Έμ‘°ν•˜μ„Έμš”:

list.index(x[, start[, end]])
값이 x와 같은 첫 번째 ν•­λͺ©μ˜ 0 기반 인덱슀λ₯Ό λ°˜ν™˜ν•©λ‹ˆλ‹€. κ·ΈλŸ¬ν•œ ν•­λͺ©μ΄ μ—†λŠ” 경우 ValueError κ°€ λ°œμƒν•©λ‹ˆλ‹€.

선택적인 인수 start와 endλŠ” 슬라이슀 ν‘œκΈ°λ²•μ—μ„œμ˜ 식별에 ν•΄λ‹Ήν•˜λ©° 리슀트의 νŠΉμ • ν•˜μœ„ μ‹œν€€μŠ€λ‘œ 검색을 μ œν•œν•˜λŠ” 데 μ‚¬μš©λ©λ‹ˆλ‹€. λ°˜ν™˜λœ μΈλ±μŠ€λŠ” μ‹œμž‘ μΈμžκ°€ μ•„λ‹Œ 전체 μ‹œν€€μŠ€μ˜ μ‹œμž‘μ„ κΈ°μ€€μœΌλ‘œ κ³„μ‚°λ©λ‹ˆλ‹€.<|im_end|>
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train heegyu/Synatra-7B-v0.3-Translation-glaive