BeibitDS commited on
Commit
dd31236
·
verified ·
1 Parent(s): eb8bb98

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -13,7 +13,7 @@ tags:
13
 
14
  # Uploaded model
15
 
16
- - **Developed by:** TilQazyna
17
  - **License:** apache-2.0
18
  - **Finetuned from model :** Meta-Llama-3-8B
19
 
@@ -29,11 +29,11 @@ To install the necessary dependencies, use the following commands:
29
  ```python
30
  from transformers import AutoTokenizer, AutoModelForCausalLM
31
 
32
- model_name = "TilQazyna/tq-kaz-instruct-1"
33
  hf_token = "<ENTER YOUR TOKEN>"
34
 
35
  # enable load_in_4bit=True for faster results but slighlty lower accuracy
36
- model = AutoModelForCausalLM.from_pretrained(model_name,load_in_4bit=True, use_auth_token=hf_token)
37
  tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
38
  ```
39
 
 
13
 
14
  # Uploaded model
15
 
16
+ - **Developed by:** Til-Qazyna
17
  - **License:** apache-2.0
18
  - **Finetuned from model :** Meta-Llama-3-8B
19
 
 
29
  ```python
30
  from transformers import AutoTokenizer, AutoModelForCausalLM
31
 
32
+ model_name = "TilQazyna/llama-kaz-instruct-8B-1"
33
  hf_token = "<ENTER YOUR TOKEN>"
34
 
35
  # enable load_in_4bit=True for faster results but slighlty lower accuracy
36
+ model = AutoModelForCausalLM.from_pretrained(model_name, load_in_8bit=True, use_auth_token=hf_token)
37
  tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
38
  ```
39