g-ronimo commited on
Commit
62cf1c9
1 Parent(s): e2764a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -5,23 +5,20 @@ license: other
5
  license_name: llama3
6
  ---
7
 
8
- # Model Card for Model ID
9
- llama3-8b trained in 10k longest samples of OpenHermes
10
 
11
- ## Usage
12
  ```python
13
  from transformers import AutoModelForCausalLM, AutoTokenizer
14
  import torch
15
 
16
  model_path = "g-ronimo/llama3-8b-SlimHermes"
17
-
18
  model = AutoModelForCausalLM.from_pretrained(
19
  model_path,
20
- # return_dict=True,
21
  torch_dtype=torch.bfloat16,
22
  device_map="auto",
23
  )
24
-
25
  tokenizer = AutoTokenizer.from_pretrained(model_path)
26
 
27
  messages = [
@@ -40,6 +37,8 @@ output = tokenizer.decode(output_tokens[0], skip_special_tokens=False)
40
  print(output)
41
  ```
42
 
 
 
43
  ```
44
  <|im_start|>system
45
  Talk like a pirate.<|im_end|>
 
5
  license_name: llama3
6
  ---
7
 
8
+ # g-ronimo/llama3-8b-SlimHermes
9
+ * `meta-llama/Meta-Llama-3-8B` trained on 10k of longest samples from `teknium/OpenHermes-2.5`
10
 
11
+ ## Sample Usage
12
  ```python
13
  from transformers import AutoModelForCausalLM, AutoTokenizer
14
  import torch
15
 
16
  model_path = "g-ronimo/llama3-8b-SlimHermes"
 
17
  model = AutoModelForCausalLM.from_pretrained(
18
  model_path,
 
19
  torch_dtype=torch.bfloat16,
20
  device_map="auto",
21
  )
 
22
  tokenizer = AutoTokenizer.from_pretrained(model_path)
23
 
24
  messages = [
 
37
  print(output)
38
  ```
39
 
40
+ ## Sample Output
41
+
42
  ```
43
  <|im_start|>system
44
  Talk like a pirate.<|im_end|>