Ben Burtenshaw commited on
Commit
7503ca9
β€’
1 Parent(s): fc828f1

fix index error in perspectives

Browse files
pages/2_πŸ‘©πŸΌβ€πŸ”¬ Describe Domain.py CHANGED
@@ -113,7 +113,6 @@ with tab_domain_perspectives:
113
 
114
  if st.button("Add Perspective", key="add_perspective"):
115
  n = len(perspectives)
116
- value = DEFAULT_PERSPECTIVES[n] if n < N_PERSPECTIVES else ""
117
  perspectives.append(
118
  perspectives_container.text_input(f"Domain Perspective {n + 1}", value="")
119
  )
@@ -142,7 +141,6 @@ with tab_domain_topics:
142
 
143
  if st.button("Add Topic", key="add_topic"):
144
  n = len(topics)
145
- value = DEFAULT_TOPICS[n] if n < N_TOPICS else ""
146
  topics.append(topics_container.text_input(f"Domain Topics {n + 1}", value=""))
147
 
148
  st.session_state["topics"] = topics
 
113
 
114
  if st.button("Add Perspective", key="add_perspective"):
115
  n = len(perspectives)
 
116
  perspectives.append(
117
  perspectives_container.text_input(f"Domain Perspective {n + 1}", value="")
118
  )
 
141
 
142
  if st.button("Add Topic", key="add_topic"):
143
  n = len(topics)
 
144
  topics.append(topics_container.text_input(f"Domain Topics {n + 1}", value=""))
145
 
146
  st.session_state["topics"] = topics
pages/3_🌱 Generate Dataset.py CHANGED
@@ -36,8 +36,9 @@ st.write(
36
  "Now we need to define the configuration for the pipeline that will generate the synthetic data."
37
  )
38
  st.write(
39
- "⚠️ Model and parameter choice significantly affect the quality of the generated data. \
40
- We reccomend that you start with a few samples and review the data. The scale up from there."
 
41
  )
42
 
43
 
@@ -91,7 +92,7 @@ self_intruct_num_generations = st.slider(
91
  "Number of generations for self-instruction", 1, 10, 2
92
  )
93
  domain_expert_num_generations = st.slider(
94
- "Number of generations for domain expert", 1, 10, 2
95
  )
96
  self_instruct_temperature = st.slider("Temperature for self-instruction", 0.1, 1.0, 0.9)
97
  domain_expert_temperature = st.slider("Temperature for domain expert", 0.1, 1.0, 0.9)
@@ -186,5 +187,19 @@ if all(
186
  "πŸ‘©β€πŸš€ If you want to customise the pipeline take a look in `pipeline.py` and teh [distilabel docs](https://distilabel.argilla.io/)"
187
  )
188
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  else:
190
  st.info("Please fill all the required fields.")
 
36
  "Now we need to define the configuration for the pipeline that will generate the synthetic data."
37
  )
38
  st.write(
39
+ "⚠️ Model and parameter choices significantly affect the quality of the generated data. \
40
+ We reccomend that you start with generating a few samples and review the data. Then scale up from there. \
41
+ You can run the pipeline multiple times with different configurations and append it to the same Argilla dataset."
42
  )
43
 
44
 
 
92
  "Number of generations for self-instruction", 1, 10, 2
93
  )
94
  domain_expert_num_generations = st.slider(
95
+ "Number of generations for domain expert response", 1, 10, 2
96
  )
97
  self_instruct_temperature = st.slider("Temperature for self-instruction", 0.1, 1.0, 0.9)
98
  domain_expert_temperature = st.slider("Temperature for domain expert", 0.1, 1.0, 0.9)
 
187
  "πŸ‘©β€πŸš€ If you want to customise the pipeline take a look in `pipeline.py` and teh [distilabel docs](https://distilabel.argilla.io/)"
188
  )
189
 
190
+ st.markdown(
191
+ "πŸš€ Once you've run the pipeline your records will be available in the Argilla space"
192
+ )
193
+
194
+ st.link_button("πŸ”— Argilla Space", argilla_url)
195
+
196
+ st.markdown("Once you've reviewed the data, you can publish it on the next page:")
197
+
198
+ st.page_link(
199
+ page="pages/4_πŸ” Review Generated Data.py",
200
+ label="Review Generated Data",
201
+ icon="πŸ”",
202
+ )
203
+
204
  else:
205
  st.info("Please fill all the required fields.")