tokutsu commited on
Commit
8ef01ac
1 Parent(s): 918ffed

Update README

Browse files
Files changed (1) hide show
  1. README.md +6 -7
README.md CHANGED
@@ -21,7 +21,7 @@ datasets:
21
 
22
  ## Overview
23
 
24
- This is a fine-tuned [`llm-jp-3-13b-it`](https://huggingface.co/tokutsu/llm-jp-3-13b-it) model for [ELYZA-tasks-100](https://huggingface.co/datasets/elyza/ELYZA-tasks-100). The model was trained on ELYZA-tasks-100 and the [ichikara-instruction dataset](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/).
25
 
26
  ## Usage
27
 
@@ -36,7 +36,6 @@ model, tokenizer = FastLanguageModel.from_pretrained(
36
  model_name=model_id,
37
  dtype=None,
38
  load_in_4bit=True,
39
- trust_remote_code=True,
40
  )
41
  FastLanguageModel.for_inference(model)
42
 
@@ -47,11 +46,11 @@ prompt = """### 指示
47
  """
48
 
49
  inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
50
- outputs = model(**inputs,
51
- max_new_tokens=512,
52
- use_cache=True,
53
- do_sample=False,
54
- repetition_penalty=1.2)
55
  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
56
  ```
57
 
 
21
 
22
  ## Overview
23
 
24
+ This is a fine-tuned [llm-jp-3-13b-it](https://huggingface.co/tokutsu/llm-jp-3-13b-it) model for [ELYZA-tasks-100](https://huggingface.co/datasets/elyza/ELYZA-tasks-100). The model was trained on ELYZA-tasks-100 and the [ichikara-instruction dataset](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/).
25
 
26
  ## Usage
27
 
 
36
  model_name=model_id,
37
  dtype=None,
38
  load_in_4bit=True,
 
39
  )
40
  FastLanguageModel.for_inference(model)
41
 
 
46
  """
47
 
48
  inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
49
+ outputs = model.generate(**inputs,
50
+ max_new_tokens=512,
51
+ use_cache=True,
52
+ do_sample=False,
53
+ repetition_penalty=1.2)
54
  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
55
  ```
56