Text Generation
Transformers
PyTorch
English
llama
Eval Results
Inference Endpoints
text-generation-inference
Pankaj Mathur commited on
Commit
122b007
1 Parent(s): 5451a37

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -5,19 +5,20 @@ language:
5
  library_name: transformers
6
  pipeline_tag: text-generation
7
  ---
8
- # Wizardlm Alpaca Dolly Orca Open_LLaMa_13b
9
- An Open_LLaMA-7B model trained on custom explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
 
10
 
11
 
12
  # Dataset
13
 
14
- We trained [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) on custom explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
15
 
16
  We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
17
 
18
- This helps student model aka [wizardlm_alpaca_dolly_orca_open_llama_7b](https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_7b) to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
19
 
20
- Please see below example usage how the **System** prompt is added before each *instruction*.
21
 
22
  # Training
23
 
 
5
  library_name: transformers
6
  pipeline_tag: text-generation
7
  ---
8
+ # orca_mini_7b
9
+
10
+ An [OpenLLaMa-7B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
11
 
12
 
13
  # Dataset
14
 
15
+ We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
16
 
17
  We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
18
 
19
+ This helps student model aka [wizardlm_alpaca_dolly_orca_open_llama_13b](https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_13b) to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
20
 
21
+ Please see below example usage how the **System** prompt is added before each **instruction**.
22
 
23
  # Training
24