hamishivi commited on
Commit
e5f27bf
1 Parent(s): 6400275

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -7,12 +7,12 @@ language:
7
 
8
  # Open-Instruct Dolly 7B
9
 
10
- This model is a 7B LLaMa model finetuned on the Dolly dataset. *please note this is a model diff - see below for usage instructions*.
11
 
12
- This was trained as part of the paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](arxiv.org/abs/xxxx).
13
  The codebase used to train and evaluate this model can be found at [https://github.com/allenai/open-instruct](https://github.com/allenai/open-instruct).
14
 
15
- This model is licensed under a modified LlaMa license, see License.txt for details.
16
 
17
  ## Usage
18
 
@@ -31,7 +31,7 @@ And you will have a recovered model! Note this takes up a decent amount of RAM,
31
 
32
  ## Input Format
33
 
34
- The model is trained to use the following format:
35
  ```
36
  <|user|>
37
  Your message here!
@@ -42,7 +42,7 @@ For best results, format all inputs in this manner.
42
 
43
  ## Performance
44
 
45
- Here is the performance of this model across benchmarks explored in our paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](arxiv.org/abs/xxxx):
46
 
47
  | MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
48
  |:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|
 
7
 
8
  # Open-Instruct Dolly 7B
9
 
10
+ This model is a 7B LLaMa model finetuned on the Dolly dataset. *Please note this is a model diff - see below for usage instructions*.
11
 
12
+ This was trained as part of the paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751).
13
  The codebase used to train and evaluate this model can be found at [https://github.com/allenai/open-instruct](https://github.com/allenai/open-instruct).
14
 
15
+ This model is licensed under the AI model license given in LICENSE.txt along with the original Llama license (llama_license.txt).
16
 
17
  ## Usage
18
 
 
31
 
32
  ## Input Format
33
 
34
+ The model is trained to use the following format (note the newlines):
35
  ```
36
  <|user|>
37
  Your message here!
 
42
 
43
  ## Performance
44
 
45
+ Here is the performance of this model across benchmarks explored in our paper [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://arxiv.org/abs/2306.04751):
46
 
47
  | MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
48
  |:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|