jeanbaptdzd/open-finance-llm-8b at 5ac5a91fa2650395b5a5f7003524875e4d1cb15d

open-finance-llm-8b

232 kB

3 contributors

History: 33 commits

jeanbaptdzd

Fix critical bugs: OOM errors, race conditions, truncation, and French language support

5ac5a91 about 1 month ago

app
Fix critical bugs: OOM errors, race conditions, truncation, and French language support about 1 month ago
scripts
Update to vLLM 0.9.2 with Qwen3 support, remove PRIIPS functionality, add HF Space validation hook about 1 month ago
tests
Rename vllm.py to transformers_provider.py - clarify implementation and force rebuild about 1 month ago
.build_trigger
25 Bytes

Force Space rebuild - Transformers migration about 1 month ago
.dockerignore
517 Bytes

Initial commit: FastAPI service with OpenAI-compatible API and PRIIPs extraction about 2 months ago
.gitignore
110 Bytes

feat: FastAPI vLLM service with OpenAI-compatible endpoints and PRIIPs extractor about 2 months ago
.gitkeep
0 Bytes

Trigger Space rebuild with Transformers about 1 month ago
Dockerfile
3.24 kB

Fix critical bugs: OOM errors, race conditions, truncation, and French language support about 1 month ago
FINAL_TEST_REPORT.md
8.3 kB

Add final test report - all issues resolved, production ready about 1 month ago
FIXES_SUMMARY.md
5.08 kB

Add GPU memory cleanup and fix OOM errors - cleanup cache after each inference about 1 month ago
LICENSE
11.3 kB

Update to vLLM 0.9.2 with Qwen3 support, remove PRIIPS functionality, add HF Space validation hook about 1 month ago
PERFORMANCE_REPORT.md
8.67 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
README.md
4.02 kB

Migrate from vLLM to Transformers library about 1 month ago
STATUS.md
5.34 kB

Add GPU memory cleanup and fix OOM errors - cleanup cache after each inference about 1 month ago
analyze_performance.py
10.4 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
memory_test_results.txt
11.8 kB

Fix critical bugs: OOM errors, race conditions, truncation, and French language support about 1 month ago
requirements-dev.txt
128 Bytes

Refactor: Remove RAG, upgrade vLLM 0.9.2, add optimization mode about 1 month ago
requirements.txt
343 Bytes

Migrate from vLLM to Transformers library about 1 month ago
test_advanced_finance.py
8.73 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
test_finance_final.py
9.31 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
test_finance_improved.py
10.3 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
test_finance_queries.py
8.08 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
test_french_simple.sh
1.06 kB

Add GPU memory cleanup and fix OOM errors - cleanup cache after each inference about 1 month ago
test_generation_fix.sh
1.4 kB

Add GPU memory cleanup and fix OOM errors - cleanup cache after each inference about 1 month ago
test_memory_stress.py
11.7 kB

Fix critical bugs: OOM errors, race conditions, truncation, and French language support about 1 month ago
test_results.txt
32.4 kB

Fix generation: increase tokens for complete answers, add EOS handling about 1 month ago
test_service.py
3.98 kB

Update Space URL references to open-finance-llm-8b about 1 month ago