Hugging Face's logo

dfurman
/
Mistral-7B-Instruct-v0.1

Text Generation
PEFT
Safetensors
mistral
conversational
Model card Files Community
dfurman commited on
Commit
dff6033
·
1 Parent(s): 344ca4f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -49,7 +49,7 @@ We use Eleuther.AI's [Language Model Evaluation Harness](https://github.com/Eleu
49
  It took ~1 hour to train 1 epoch on 1x A100.
50
 
51
  Prompt format:
52
- This model (and all my future releases) use [ChatML](https://huggingface.co/docs/transformers/chat_templating#what-template-should-i-use) prompt format.
53
 
54
  ```
55
  <|im_start|>system
@@ -57,9 +57,11 @@ You are a helpful assistant.<|im_end|>
57
  <|im_start|>user
58
  {prompt}<|im_end|>
59
  <|im_start|>assistant
60
- ### Training Hyperparameters
61
  ```
62
 
 
 
 
63
  We use the [SFTTrainer](https://huggingface.co/docs/trl/main/en/sft_trainer) from `trl` to fine-tune llms on instruction-following datasets.
64
 
65
  The following `TrainingArguments` config was used:
 
49
  It took ~1 hour to train 1 epoch on 1x A100.
50
 
51
  Prompt format:
52
+ This model (and all my future releases) uses the [ChatML](https://huggingface.co/docs/transformers/chat_templating#what-template-should-i-use) prompt format, which was developed by OpenAI.
53
 
54
  ```
55
  <|im_start|>system
 
57
  <|im_start|>user
58
  {prompt}<|im_end|>
59
  <|im_start|>assistant
 
60
  ```
61
 
62
+ ### Training Hyperparameters
63
+
64
+
65
  We use the [SFTTrainer](https://huggingface.co/docs/trl/main/en/sft_trainer) from `trl` to fine-tune llms on instruction-following datasets.
66
 
67
  The following `TrainingArguments` config was used: