Commits · ButterM40/Roleplay-Chat-Box

Fix: Use Qwen3-0.6B (correct model) with proper PEFT adapter switching via set_adapter()

f92a42b

Running

ButterM40 commited on Nov 20

Add lightweight character manager - uses one base model with adapter swapping for HF Spaces

de2021f

ButterM40 commited on Nov 20

Switch from Gradio to Streamlit - more stable for HF Spaces

9fb3586

ButterM40 commited on Nov 20

Fix HF Space: update SDK version, add error handling, improve README

7f7c489

ButterM40 commited on Nov 20

Remove schema-breaking features: use Gradio 3.35.0, remove .then() chains and HTML components

bad3b4b

ButterM40 commited on Nov 20

Fix Gradio schema error: Use v3.40.1 and simplified interface

390f796

ButterM40 commited on Nov 20

Fix Gradio deployment errors

d207a2b

ButterM40 commited on Nov 20

Fix: Simplified Gradio interface for v3.x compatibility

cad5bb4

ButterM40 commited on Nov 20

🔧 Fixed Gradio TypeError and share warning

e981624

ButterM40 commited on Nov 20

🔧 Fixed TypeError by pinning Gradio to stable version

6b485cf

ButterM40 commited on Nov 20

🔧 Fixed LoRA adapter loading and Gradio interface

52eea3a

ButterM40 commited on Nov 20

Fix character isolation: create separate model instances to prevent adapter interference

8575a1c

ButterM40 commited on Nov 20

Implement proper adapter switching instead of multiple models

eb874dd

ButterM40 commited on Nov 20

Fix adapter interference: create dedicated model instances per character

7304d60

ButterM40 commited on Nov 20

Fix parameter name: user_input -> user_message

373cd0c

ButterM40 commited on Nov 20

Fix syntax error: add missing except clause and fix indentation

a94158b

ButterM40 commited on Nov 20

Comprehensive fix: Update transformers for Qwen3 support and improve LoRA adapter compatibility

bf6aead

ButterM40 commited on Nov 20

CRITICAL FIX: Use Qwen/Qwen3-0.6B to match LoRA adapter training base model

aaf38b0

ButterM40 commited on Nov 20

Fix base model to Qwen2.5-0.5B and clean LoRA adapter config compatibility

4b68f15

ButterM40 commited on Nov 20

Fix LoRA adapter compatibility issues and add robust fallbacks

114bef9

ButterM40 commited on Nov 20

Add missing samsung_employee.svg avatar file

44d5aa5

ButterM40 commited on Nov 20

Fix API endpoints to match frontend expectations - resolve 404 errors

e73d728

ButterM40 commited on Nov 20

Add complete LoRA adapter files and base model configuration for proper character loading

200bff1

ButterM40 commited on Nov 20

Deploy actual React-style frontend with FastAPI backend

c2db707

ButterM40 commited on Nov 20

Fix metadata: shorten description and correct app_file

8955d02

ButterM40 commited on Nov 20

Deploy Roleplay Chat Box - optimized version without large files

7e68852

ButterM40 commited on Nov 20

initial commit

4523cf6
verified

ButterM40 commited on Nov 20

Duplicate from gradio-templates/chatbot

e0c473c
verified

ButterM40

pngwn HF Staff commited on Nov 20

Spaces:

ButterM40
/

Roleplay-Chat-Box

Running

Commit History

Fix: Use Qwen3-0.6B (correct model) with proper PEFT adapter switching via set_adapter()

f92a42b

Running

Add lightweight character manager - uses one base model with adapter swapping for HF Spaces

de2021f

Switch from Gradio to Streamlit - more stable for HF Spaces

9fb3586

Fix HF Space: update SDK version, add error handling, improve README

7f7c489

Remove schema-breaking features: use Gradio 3.35.0, remove .then() chains and HTML components

bad3b4b

Fix Gradio schema error: Use v3.40.1 and simplified interface

390f796

Fix Gradio deployment errors

d207a2b

Fix: Simplified Gradio interface for v3.x compatibility

cad5bb4

🔧 Fixed Gradio TypeError and share warning

e981624

🔧 Fixed TypeError by pinning Gradio to stable version

6b485cf

🔧 Fixed LoRA adapter loading and Gradio interface

52eea3a

Fix character isolation: create separate model instances to prevent adapter interference

8575a1c

Implement proper adapter switching instead of multiple models

eb874dd

Fix adapter interference: create dedicated model instances per character

7304d60

Fix parameter name: user_input -> user_message

373cd0c

Fix syntax error: add missing except clause and fix indentation

a94158b

Comprehensive fix: Update transformers for Qwen3 support and improve LoRA adapter compatibility

bf6aead

CRITICAL FIX: Use Qwen/Qwen3-0.6B to match LoRA adapter training base model

aaf38b0

Fix base model to Qwen2.5-0.5B and clean LoRA adapter config compatibility

4b68f15

Fix LoRA adapter compatibility issues and add robust fallbacks

114bef9

Add missing samsung_employee.svg avatar file

44d5aa5

Fix API endpoints to match frontend expectations - resolve 404 errors

e73d728

Add complete LoRA adapter files and base model configuration for proper character loading

200bff1

Deploy actual React-style frontend with FastAPI backend

c2db707

Fix metadata: shorten description and correct app_file

8955d02

Deploy Roleplay Chat Box - optimized version without large files

7e68852

initial commit

4523cf6
verified

Duplicate from gradio-templates/chatbot

e0c473c
verified

Commit History

Fix: Use Qwen3-0.6B (correct model) with proper PEFT adapter switching via set_adapter() f92a42b Running

Add lightweight character manager - uses one base model with adapter swapping for HF Spaces de2021f

Switch from Gradio to Streamlit - more stable for HF Spaces 9fb3586

Fix HF Space: update SDK version, add error handling, improve README 7f7c489

Remove schema-breaking features: use Gradio 3.35.0, remove .then() chains and HTML components bad3b4b

Fix Gradio schema error: Use v3.40.1 and simplified interface 390f796

Fix Gradio deployment errors d207a2b

Fix: Simplified Gradio interface for v3.x compatibility cad5bb4

🔧 Fixed Gradio TypeError and share warning e981624

🔧 Fixed TypeError by pinning Gradio to stable version 6b485cf

🔧 Fixed LoRA adapter loading and Gradio interface 52eea3a

Fix character isolation: create separate model instances to prevent adapter interference 8575a1c

Implement proper adapter switching instead of multiple models eb874dd

Fix adapter interference: create dedicated model instances per character 7304d60

Fix parameter name: user_input -> user_message 373cd0c

Fix syntax error: add missing except clause and fix indentation a94158b

Comprehensive fix: Update transformers for Qwen3 support and improve LoRA adapter compatibility bf6aead

CRITICAL FIX: Use Qwen/Qwen3-0.6B to match LoRA adapter training base model aaf38b0

Fix base model to Qwen2.5-0.5B and clean LoRA adapter config compatibility 4b68f15

Fix LoRA adapter compatibility issues and add robust fallbacks 114bef9

Add missing samsung_employee.svg avatar file 44d5aa5

Fix API endpoints to match frontend expectations - resolve 404 errors e73d728

Add complete LoRA adapter files and base model configuration for proper character loading 200bff1

Deploy actual React-style frontend with FastAPI backend c2db707

Fix metadata: shorten description and correct app_file 8955d02

Deploy Roleplay Chat Box - optimized version without large files 7e68852

initial commit 4523cf6 verified

Duplicate from gradio-templates/chatbot e0c473c verified

Fix: Use Qwen3-0.6B (correct model) with proper PEFT adapter switching via set_adapter()

f92a42b

Running

Add lightweight character manager - uses one base model with adapter swapping for HF Spaces

de2021f

Switch from Gradio to Streamlit - more stable for HF Spaces

9fb3586

Fix HF Space: update SDK version, add error handling, improve README

7f7c489

Remove schema-breaking features: use Gradio 3.35.0, remove .then() chains and HTML components

bad3b4b

Fix Gradio schema error: Use v3.40.1 and simplified interface

390f796

Fix Gradio deployment errors

d207a2b

Fix: Simplified Gradio interface for v3.x compatibility

cad5bb4

🔧 Fixed Gradio TypeError and share warning

e981624

🔧 Fixed TypeError by pinning Gradio to stable version

6b485cf

🔧 Fixed LoRA adapter loading and Gradio interface

52eea3a

Fix character isolation: create separate model instances to prevent adapter interference

8575a1c

Implement proper adapter switching instead of multiple models

eb874dd

Fix adapter interference: create dedicated model instances per character

7304d60

Fix parameter name: user_input -> user_message

373cd0c

Fix syntax error: add missing except clause and fix indentation

a94158b

Comprehensive fix: Update transformers for Qwen3 support and improve LoRA adapter compatibility

bf6aead

CRITICAL FIX: Use Qwen/Qwen3-0.6B to match LoRA adapter training base model

aaf38b0

Fix base model to Qwen2.5-0.5B and clean LoRA adapter config compatibility

4b68f15

Fix LoRA adapter compatibility issues and add robust fallbacks

114bef9

Add missing samsung_employee.svg avatar file

44d5aa5

Fix API endpoints to match frontend expectations - resolve 404 errors

e73d728

Add complete LoRA adapter files and base model configuration for proper character loading

200bff1

Deploy actual React-style frontend with FastAPI backend

c2db707

Fix metadata: shorten description and correct app_file

8955d02

Deploy Roleplay Chat Box - optimized version without large files

7e68852

initial commit

4523cf6
verified

Duplicate from gradio-templates/chatbot

e0c473c
verified