Spaces:

jeanbaptdzd
/

open-finance-llm-8b

Paused

App Files Files Community

open-finance-llm-8b / app

64.5 kB

3 contributors

History: 63 commits

jeanbaptdzd's picture

fix: vLLM tool calling - enable by default with hermes parser

7239fe3 about 1 month ago

middleware
feat: Add rate limiting, stats tracking, and fix critical issues about 2 months ago
models
Fix OpenAI API compatibility: support tool_choice='required' and response_format about 2 months ago
providers
fix: vLLM tool calling - enable by default with hermes parser about 1 month ago
routers
Fix device placement for tokenizer outputs before model inference about 1 month ago
utils
Refactor: Address code shortcomings and align with HF best practices about 1 month ago
__init__.py

58 Bytes

Refactor: Address code shortcomings and align with HF best practices about 1 month ago
config.py

1.16 kB

Fix model ID and improve memory management about 2 months ago
main.py

3.65 kB

Add error handling for invalid log level configuration about 1 month ago
middleware.py

1.73 kB

Fix model ID and improve memory management about 2 months ago