rombodawg commited on
Commit
2f66107
1 Parent(s): b4985a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -12,7 +12,8 @@ For anyone that is new to coding and training Ai, all your really have to edit i
12
  3. (alpaca_prompt =) Change the prompt format, this one is setup to meet llama-3-8b-instruct format, but match it to your specifications.
13
  4. (dataset = load_dataset("Replete-AI/code-test-dataset", split = "train")) What dataset you are using from huggingface
14
  5. (model.push_to_hub_merged("rombodawg/test_dataset_Codellama-3-8B", tokenizer, save_method = "merged_16bit", token = ""))
15
- For the above you need to change "rombodawg" to your Hugginface name, "test_dataset_Codellama-3-8B" to the model name you want saved as, and in token = "" you need to put your huggingface write token so the model can be saved.
 
16
 
17
 
18
  ```Python
@@ -153,6 +154,7 @@ trainer = SFTTrainer(
153
  ```
154
 
155
 
 
156
  ```Python
157
  trainer_stats = trainer.train()
158
  model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
 
12
  3. (alpaca_prompt =) Change the prompt format, this one is setup to meet llama-3-8b-instruct format, but match it to your specifications.
13
  4. (dataset = load_dataset("Replete-AI/code-test-dataset", split = "train")) What dataset you are using from huggingface
14
  5. (model.push_to_hub_merged("rombodawg/test_dataset_Codellama-3-8B", tokenizer, save_method = "merged_16bit", token = ""))
15
+
16
+ For the above you need to change "rombodawg" to your Hugginface name, "test_dataset_Codellama-3-8B" to the model name you want saved as, and in token = "" you need to put your huggingface write token so the model can be saved.
17
 
18
 
19
  ```Python
 
154
  ```
155
 
156
 
157
+
158
  ```Python
159
  trainer_stats = trainer.train()
160
  model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)