PEFT
Safetensors
English
Japanese
h-iida commited on
Commit
e6aaa22
·
verified ·
1 Parent(s): 161bb66

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -28,18 +28,18 @@ This is a model that applies LLM2Vec to Llama2. Only the PEFT Adapter is distrib
28
  - **Repository:** https://github.com/McGill-NLP/llm2vec
29
  - **Paper:** https://arxiv.org/abs/2404.05961
30
 
31
- ## Usage
32
 
33
  - Please see [original LLM2Vec repo](https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp#usage)
34
 
35
- ## Training Details
36
 
37
- ### Training Data
38
 
39
  - [wikitext](https://huggingface.co/datasets/Salesforce/wikitext)
40
 
41
 
42
- #### Training Hyperparameter
43
  - batch_size: 64,
44
  - gradient_accumulation_steps: 1
45
  - max_seq_length": 512,
@@ -51,7 +51,7 @@ This is a model that applies LLM2Vec to Llama2. Only the PEFT Adapter is distrib
51
  - bf16: true
52
  - gradient_checkpointing: true
53
 
54
- #### Accelerator Settings
55
  - deepspeed_config:
56
  - gradient_accumulation_steps: 1
57
  - gradient_clipping: 1.0
@@ -77,7 +77,7 @@ This is a model that applies LLM2Vec to Llama2. Only the PEFT Adapter is distrib
77
  - quse_cpu: false
78
 
79
 
80
- ### Framework versions
81
 
82
  - Python: 3.12.3
83
  - PEFT 0.11.1
 
28
  - **Repository:** https://github.com/McGill-NLP/llm2vec
29
  - **Paper:** https://arxiv.org/abs/2404.05961
30
 
31
+ # Usage
32
 
33
  - Please see [original LLM2Vec repo](https://huggingface.co/McGill-NLP/LLM2Vec-Llama-2-7b-chat-hf-mntp#usage)
34
 
35
+ # Training Details
36
 
37
+ ## Training Data
38
 
39
  - [wikitext](https://huggingface.co/datasets/Salesforce/wikitext)
40
 
41
 
42
+ ## Training Hyperparameter
43
  - batch_size: 64,
44
  - gradient_accumulation_steps: 1
45
  - max_seq_length": 512,
 
51
  - bf16: true
52
  - gradient_checkpointing: true
53
 
54
+ ## Accelerator Settings
55
  - deepspeed_config:
56
  - gradient_accumulation_steps: 1
57
  - gradient_clipping: 1.0
 
77
  - quse_cpu: false
78
 
79
 
80
+ ## Framework versions
81
 
82
  - Python: 3.12.3
83
  - PEFT 0.11.1