WasamiKirua commited on
Commit
4bb1441
·
verified ·
1 Parent(s): 7243f2d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -21,31 +21,6 @@ datasets:
21
  - WasamiKirua/haiku-ita-v0.2
22
  ---
23
 
24
- # Uploaded model
25
-
26
- - **Developed by:** WasamiKirua
27
- - **License:** apache-2.0
28
- - **Finetuned from model :** unsloth/qwen2.5-7b-bnb-4bit
29
-
30
- This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
31
-
32
- You can use it with ollama (Modelfile):
33
-
34
- ```
35
- FROM {__FILE_LOCATION__}
36
- TEMPLATE """{{ if .System }}<|im_start|>system
37
- {{ .System }}<|im_end|>
38
- {{ end }}{{ if .Prompt }}<|im_start|>user
39
- {{ .Prompt }}<|im_end|>
40
- {{ end }}<|im_start|>assistant
41
- {{ .Response }}<|im_end|>
42
- """
43
- PARAMETER stop "<|im_start|>"
44
- PARAMETER stop "<|im_end|>"
45
- PARAMETER temperature 1.5
46
- PARAMETER min_p 0.1
47
- ```
48
-
49
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
50
 
51
  ## Model Details
@@ -129,4 +104,29 @@ To mitigate misuse and ensure Samantha is used as intended:
129
  - **Clear usage guidelines**: Make it clear that Samantha is not a substitute for professional mental health care and that its recommendations should not be considered professional advice.
130
  - **Regular updates and monitoring**: Continuously monitor the model's behavior and responses, updating it regularly to improve its ability to recognize misuse, inappropriate requests, and limitations in its capabilities.
131
 
132
- By recognizing the risks and limitations, the deployment of Samantha can be shaped to minimize misuse and maximize its positive, supportive potential.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  - WasamiKirua/haiku-ita-v0.2
22
  ---
23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
25
 
26
  ## Model Details
 
104
  - **Clear usage guidelines**: Make it clear that Samantha is not a substitute for professional mental health care and that its recommendations should not be considered professional advice.
105
  - **Regular updates and monitoring**: Continuously monitor the model's behavior and responses, updating it regularly to improve its ability to recognize misuse, inappropriate requests, and limitations in its capabilities.
106
 
107
+ By recognizing the risks and limitations, the deployment of Samantha can be shaped to minimize misuse and maximize its positive, supportive potential.
108
+
109
+ # Uploaded model
110
+
111
+ - **Developed by:** WasamiKirua
112
+ - **License:** apache-2.0
113
+ - **Finetuned from model :** unsloth/qwen2.5-7b-bnb-4bit
114
+
115
+ This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
116
+
117
+ You can use it with ollama (Modelfile):
118
+
119
+ ```
120
+ FROM {__FILE_LOCATION__}
121
+ TEMPLATE """{{ if .System }}<|im_start|>system
122
+ {{ .System }}<|im_end|>
123
+ {{ end }}{{ if .Prompt }}<|im_start|>user
124
+ {{ .Prompt }}<|im_end|>
125
+ {{ end }}<|im_start|>assistant
126
+ {{ .Response }}<|im_end|>
127
+ """
128
+ PARAMETER stop "<|im_start|>"
129
+ PARAMETER stop "<|im_end|>"
130
+ PARAMETER temperature 1.5
131
+ PARAMETER min_p 0.1
132
+ ```