Update README.md
Browse files
README.md
CHANGED
@@ -67,42 +67,38 @@ A: Het belang van privacy voor bedrijven is dat ze hun klanten moeten beschermen
|
|
67 |
## Uses
|
68 |
|
69 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
|
|
70 |
|
71 |
### Direct Use
|
72 |
|
73 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
74 |
|
75 |
-
|
76 |
|
77 |
### Downstream Use [optional]
|
78 |
|
79 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
80 |
-
|
81 |
-
[More Information Needed]
|
82 |
|
83 |
### Out-of-Scope Use
|
84 |
|
85 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
86 |
-
|
87 |
-
[More Information Needed]
|
88 |
|
89 |
## Bias, Risks, and Limitations
|
90 |
|
91 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
92 |
-
|
93 |
-
|
94 |
|
95 |
### Recommendations
|
96 |
|
97 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
98 |
|
99 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
100 |
|
101 |
## How to Get Started with the Model
|
102 |
|
103 |
-
|
104 |
-
|
105 |
-
[More Information Needed]
|
106 |
|
107 |
## Training Details
|
108 |
|
|
|
67 |
## Uses
|
68 |
|
69 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
70 |
+
It's a Dutch speaking drop in replacement for `meta-llama/Llama-2-7b-chat-hf` and the non-waitlist mirror `daryl149/llama-2-7b-chat-hf`.
|
71 |
|
72 |
### Direct Use
|
73 |
|
74 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
75 |
|
76 |
+
It's a Dutch speaking drop in replacement for `meta-llama/Llama-2-7b-chat-hf` and the non-waitlist mirror `daryl149/llama-2-7b-chat-hf`.
|
77 |
|
78 |
### Downstream Use [optional]
|
79 |
|
80 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
81 |
+
Do use it for further finetuning and let us know!
|
|
|
82 |
|
83 |
### Out-of-Scope Use
|
84 |
|
85 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
86 |
+
Don't be evil.
|
|
|
87 |
|
88 |
## Bias, Risks, and Limitations
|
89 |
|
90 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
91 |
+
- It's not quite perfect Dutch yet, but a very promising start.
|
92 |
+
- The model does rarely generates EOS tokens and goes on a ramble. A quick and dirty way to mitigate this is to system prompt it to generate an `</s>` after 5 sentences.
|
93 |
|
94 |
### Recommendations
|
95 |
|
96 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
97 |
|
|
|
98 |
|
99 |
## How to Get Started with the Model
|
100 |
|
101 |
+
If you already have a pipeline running llama 2 7B chat in huggingface format, just call this one instead.
|
|
|
|
|
102 |
|
103 |
## Training Details
|
104 |
|