Commits · ft-lora/llama

chore: cleanup code

8e96117

Kajlid commited on Dec 2, 2025

fix(inference): correct format of chat history and streaming response

b2faa29

Kajlid commited on Dec 2, 2025

fix(ui): remove "type" from chat interface

bdde9b4

Kajlid commited on Dec 2, 2025

fix: install requirements correctly

3fbb460

Kajlid commited on Dec 2, 2025

chore(requirements): remove llama_cpp requirement from requirements.txt

9a07ae6

Kajlid commited on Dec 2, 2025

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

00ed5b0

Kajlid commited on Dec 2, 2025

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

0c0ee51

Kajlid commited on Dec 2, 2025

fix(llm): download model from huggingface_hub before inference

364f0e9

Kajlid commited on Dec 1, 2025

Add requirements.txt

fd3c611

Kajlid commited on Dec 1, 2025

Update chat UI llm model used

dd2e964

Kajlid commited on Dec 1, 2025

feat(llm): final code for training and saving finetuned llm model to gguf

68ef1d7

Kajsa Lidin commited on Dec 1, 2025

feat(llm): final code for training and saving finetuned llm model to gguf

98ad189

Kajsa Lidin commited on Dec 1, 2025

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

db38dd7

Kajsa Lidin commited on Dec 1, 2025

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

c4e69bb

Kajsa Lidin commited on Dec 1, 2025

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

e207334

Kajsa Lidin commited on Dec 1, 2025

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

331c7f6

Kajsa Lidin commited on Dec 1, 2025

docs(readme): update huggingface configuration so that it routes to app.py

73952be

Kajlid commited on Dec 1, 2025

feat(ui): add finetuned HuggingFace model to chat UI

508d7f0

Kajlid commited on Dec 1, 2025

chore(cleanup): remove duplicate files

bfcd7e5

Kajlid commited on Dec 1, 2025

feat(ui): Add HuggingFace Space files as subfolder

ef106ac

Kajlid commited on Dec 1, 2025

fix(notebook): remove corrupted widget states through clearing output from cells

c8e3b3d

Kajsa Lidin commited on Nov 28, 2025

feat(model): finetune the llama model and store in HuggingFace

02bfcbf

Kajsa Lidin commited on Nov 28, 2025

feat(huggingface): update huggingface organization name to push finetuned model to, enable checkpointing

4ab502f

Kajsa Lidin commited on Nov 28, 2025

Skapades med Colab

1f81c21

Kajsa Lidin commited on Nov 21, 2025

Initial commit

d99e96c
unverified

Kajsa Lidin commited on Nov 21, 2025

Spaces:

ft-lora
/

llama_ui

Sleeping

Commit History

chore: cleanup code

8e96117

fix(inference): correct format of chat history and streaming response

b2faa29

fix(ui): remove "type" from chat interface

bdde9b4

fix: install requirements correctly

3fbb460

chore(requirements): remove llama_cpp requirement from requirements.txt

9a07ae6

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

00ed5b0

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

0c0ee51

fix(llm): download model from huggingface_hub before inference

364f0e9

Add requirements.txt

fd3c611

Update chat UI llm model used

dd2e964

feat(llm): final code for training and saving finetuned llm model to gguf

68ef1d7

feat(llm): final code for training and saving finetuned llm model to gguf

98ad189

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

db38dd7

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

c4e69bb

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

e207334

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

331c7f6

docs(readme): update huggingface configuration so that it routes to app.py

73952be

feat(ui): add finetuned HuggingFace model to chat UI

508d7f0

chore(cleanup): remove duplicate files

bfcd7e5

feat(ui): Add HuggingFace Space files as subfolder

ef106ac

fix(notebook): remove corrupted widget states through clearing output from cells

c8e3b3d

feat(model): finetune the llama model and store in HuggingFace

02bfcbf

feat(huggingface): update huggingface organization name to push finetuned model to, enable checkpointing

4ab502f

Skapades med Colab

1f81c21

Initial commit

d99e96c
unverified

Commit History

chore: cleanup code 8e96117

fix(inference): correct format of chat history and streaming response b2faa29

fix(ui): remove "type" from chat interface bdde9b4

fix: install requirements correctly 3fbb460

chore(requirements): remove llama_cpp requirement from requirements.txt 9a07ae6

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error 00ed5b0

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error 0c0ee51

fix(llm): download model from huggingface_hub before inference 364f0e9

Add requirements.txt fd3c611

Update chat UI llm model used dd2e964

feat(llm): final code for training and saving finetuned llm model to gguf 68ef1d7

feat(llm): final code for training and saving finetuned llm model to gguf 98ad189

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file db38dd7

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file c4e69bb

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file e207334

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file 331c7f6

docs(readme): update huggingface configuration so that it routes to app.py 73952be

feat(ui): add finetuned HuggingFace model to chat UI 508d7f0

chore(cleanup): remove duplicate files bfcd7e5

feat(ui): Add HuggingFace Space files as subfolder ef106ac

fix(notebook): remove corrupted widget states through clearing output from cells c8e3b3d

feat(model): finetune the llama model and store in HuggingFace 02bfcbf

feat(huggingface): update huggingface organization name to push finetuned model to, enable checkpointing 4ab502f

Skapades med Colab 1f81c21

Initial commit d99e96c unverified

chore: cleanup code

8e96117

fix(inference): correct format of chat history and streaming response

b2faa29

fix(ui): remove "type" from chat interface

bdde9b4

fix: install requirements correctly

3fbb460

chore(requirements): remove llama_cpp requirement from requirements.txt

9a07ae6

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

00ed5b0

fix(requirements): install llama_cpp_python via subprocess to fix HuggingFace error

0c0ee51

fix(llm): download model from huggingface_hub before inference

364f0e9

Add requirements.txt

fd3c611

Update chat UI llm model used

dd2e964

feat(llm): final code for training and saving finetuned llm model to gguf

68ef1d7

feat(llm): final code for training and saving finetuned llm model to gguf

98ad189

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

db38dd7

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

c4e69bb

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

e207334

fix(gguf): clone llama.cpp repo and convert model to gguf with convert-hf-to-gguf.py file

331c7f6

docs(readme): update huggingface configuration so that it routes to app.py

73952be

feat(ui): add finetuned HuggingFace model to chat UI

508d7f0

chore(cleanup): remove duplicate files

bfcd7e5

feat(ui): Add HuggingFace Space files as subfolder

ef106ac

fix(notebook): remove corrupted widget states through clearing output from cells

c8e3b3d

feat(model): finetune the llama model and store in HuggingFace

02bfcbf

feat(huggingface): update huggingface organization name to push finetuned model to, enable checkpointing

4ab502f

Skapades med Colab

1f81c21

Initial commit

d99e96c
unverified