wenbopan commited on
Commit
9bab0d3
1 Parent(s): 0d29b76

change name

Browse files
Files changed (1) hide show
  1. README.md +8 -6
README.md CHANGED
@@ -12,8 +12,10 @@ language:
12
 
13
  **The Faro chat model focuses on practicality and long-context modeling. It handles various downstream tasks with higher quality, delivering stable and reliable results even when inputs contain lengthy documents or complex instructions. Faro seamlessly works in both English and Chinese.**
14
 
15
- # Faro-Yi-34B-200K
16
- Faro-Yi-34B-200K is an improved [Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) with extensive instruction tuning on [Fusang-V1](https://huggingface.co/datasets/wenbopan/Fusang-v1). Compared to Yi-34B-200K, Faro-Yi-34B-200K has gained greater capability in various downstream tasks and long-context modeling thanks to the large-scale synthetic data in Fusang-V1.
 
 
17
 
18
  ## How to Use
19
 
@@ -25,7 +27,7 @@ import requests
25
  from PyPDF2 import PdfReader
26
  from vllm import LLM, SamplingParams
27
 
28
- llm = LLM(model="wenbopan/Faro-Yi-34B-200K")
29
 
30
  pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
31
  document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages
@@ -44,8 +46,8 @@ print(output[0].outputs[0].text)
44
  ```python
45
  from transformers import AutoModelForCausalLM, AutoTokenizer
46
 
47
- model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Yi-34B-200K', device_map="cuda")
48
- tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Yi-34B-200K')
49
  messages = [
50
  {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
51
  {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
@@ -57,4 +59,4 @@ response = tokenizer.decode(generated_ids[0], skip_special_tokens=True) # Aye, m
57
 
58
  </details>
59
 
60
- For more info please refer to [wenbopan/Faro-Yi-9B-200K](https://huggingface.co/wenbopan/Faro-Yi-9B-200K)
 
12
 
13
  **The Faro chat model focuses on practicality and long-context modeling. It handles various downstream tasks with higher quality, delivering stable and reliable results even when inputs contain lengthy documents or complex instructions. Faro seamlessly works in both English and Chinese.**
14
 
15
+ # Faro-Yi-34B
16
+ Faro-Yi-34B is an improved [Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) with extensive instruction tuning on [Fusang-V1](https://huggingface.co/datasets/wenbopan/Fusang-v1). Compared to Yi-34B-200K, Faro-Yi-34B has gained greater capability in various downstream tasks and long-context modeling thanks to the large-scale synthetic data in Fusang-V1.
17
+
18
+ Just like Yi-34B-200K, Faro-Yi-34B supports up to 200K context length.
19
 
20
  ## How to Use
21
 
 
27
  from PyPDF2 import PdfReader
28
  from vllm import LLM, SamplingParams
29
 
30
+ llm = LLM(model="wenbopan/Faro-Yi-34B")
31
 
32
  pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
33
  document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages
 
46
  ```python
47
  from transformers import AutoModelForCausalLM, AutoTokenizer
48
 
49
+ model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Yi-34B', device_map="cuda")
50
+ tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Yi-34B')
51
  messages = [
52
  {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
53
  {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
 
59
 
60
  </details>
61
 
62
+ For more info please refer to [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan/Faro-Yi-9B)