Commit History

Resolved triton dependency conflict by setting version to 3.3.1 as required by torch
51c2f09

dharmendra commited on

Pinned triton to version 2.2.0 for bitsandbytes compatibility
eb346bc

dharmendra commited on

Added triton to requirements.txt to resolve 'triton.ops' module error
802b786

dharmendra commited on

Ensuring correct requirements.txt content to fix 'Script' error
e19d1de

dharmendra commited on

Removed problematic comment line from requirements.txt
bdf24cc

dharmendra commited on

Added scipy to requirements.txt as a dependency for bitsandbytes
0f73f95

dharmendra commited on

Attempting bitsandbytes fix with version 0.39.0 for CUDA compatibility
9a1b384

dharmendra commited on

Fixed bitsandbytes CUDA import error by specifying version 0.41.1
ec1d865

dharmendra commited on

quantisation added
dca8b66

dharmendra commited on

Updated app.py with explicit Hugging Face login and removed model.to(device)
81d2ef5

dharmendra commited on

Added sentencepiece to requirements.txt to fix tokenizer ValueError
0e58b11

dharmendra commited on

Explicitly added protobuf to requirements.txt
74f3151

dharmendra commited on

Attempting explicit Hugging Face Hub login for gated repo access
7d7d860

dharmendra commited on

Fixed gated repo error by passing token to tokenizer
a23c36a

dharmendra commited on

Added debugging print for Hugging Face token
0242952

dharmendra commited on

Switched to Mistral 7B Instruct v0.3 model
73ab258

dharmendra commited on

Switched to Llama 3.1 8B Instruct for improved instruction following
5343cd4

dharmendra commited on

using Llama 3.1 8B instruct
d00f229

dharmendra commited on

Update app.py
0b5b6d7
verified

rathore11 commited on

Update app.py
d3140f2
verified

rathore11 commited on

14july
34826da

dharmendra commited on

Implement streaming responses for LLM API
0cb7726

dharmendra commited on

Implement streaming responses for LLM API
89183a0

dharmendra commited on

Implement streaming responses for LLM API
51e51e6

dharmendra commited on

Implement streaming responses for LLM API
48d0a68

dharmendra commited on

Implement streaming responses for LLM API
20960a5

dharmendra commited on

Implement streaming responses for LLM API
9f54674

dharmendra commited on

Implement streaming responses for LLM API
44f89b9

dharmendra commited on

Implement streaming responses for LLM API
a05ac69

dharmendra commited on

Fix: Corrected import for ConversationBufferWindowMemory
58966a1

dharmendra commited on

Fix: Implement ConversationBufferWindowMemory and pipeline generation parameters
c1073c4

dharmendra commited on

Fix: Resolve torch/torchvision dependency conflict by upgrading torch to 2.7.1
b0353ee

dharmendra commited on

Fix: Update torchvision version for torch 2.6.0 compatibility
505efd2

dharmendra commited on

Initial Docker Space setup with direct build
5601c60

dharmendra commited on

initial commit
e9ea2d4
verified

rathore11 commited on