Spaces:
Runtime error
Runtime error
Commit History
-
docs: update README to focus on data engineering tools
- Update description to emphasize systematic benchmarking for data engineering - Remove Go-related content (web services, concurrency, HTTP handlers) - Focus on Python data processing, ETL pipelines, data transformation - Add documentation generation for technical docs and API documentation - Align project structure with data engineering focus3cf16fb -
remove: redundant documentation files
- Remove README_HF_SPACES.md and DEPLOYMENT_SUMMARY.md - Keep README.md as single source of documentation - Streamline project documentation structure5cc5417 -
remove: .mb documentation files
- Remove problem_summary.mb and project_context.mb - Keep README.md as main documentation - Clean up project structure by removing outdated .mb filesc9b6ebc -
remove: Groq provider models from configuration
- Remove GPT-OSS-20B (Groq), GPT-OSS-120B (Groq), and Llama-4-Scout-17B (Groq) - Keep original models: Llama-3.1-8B-Instruct (Nebius), GPT-OSS-120B (Nebius), GEMMA-2-2B-IT (Nebius), DeepSeek-R1 (Together) - Groq provider support remains in code for future use50211fb -
feat: add Groq provider models and show provider info in UI
- Add GPT-OSS-20B, GPT-OSS-120B, and Llama-4-Scout-17B models via Groq provider - Update models_registry.py to support Groq provider with chat.completions.create - Add provider information to result dictionary in evaluator.py - Display provider info in both Evaluate and Global Leaderboard tabs - Group leaderboard by model_name and provider for accurate comparison - Enable comparison of same model across different providers05dfa56 -
feat: add DeepSeek-R1 model with Together provider
- Add deepseek-ai/DeepSeek-R1 model configuration - Configure for Together AI provider with chat.completions.create - Set standard parameters: max_new_tokens=256, temperature=0.1, top_p=0.91b57635 -
fix: aggregate Global Leaderboard by model to prevent duplicates
6e0f5df -
fix: aggregate Global Leaderboard by model to prevent duplicates
c058232 -
Add google/gemma-2-2b-it with nebius provider
58cc0ce
-
change provide for DeepSeek-R1-Distill-Llama-8B
35f20fb -
change provide for DeepSeek-R1-Distill-Llama-8B
92df651 -
change provide for DeepSeek-R1-Distill-Llama-8B
601c84c -
change provide for DeepSeek-R1-Distill-Llama-8B
13403a6 -
Fix Nebius provider to use chat.completions.create for conversational models
682dc03 -
Add GPT-OSS-120B and DeepSeek-R1-Distill-Llama-8B models with Nebius provider
2ec7e68 -
Simplify to use only text_generation for all providers - remove chat completion methods
58f426e -
Switch to Llama-3.1-8B-Instruct with Nebius provider using chat.completions.create method
b16182c -
Switch to Qwen2.5-7B-Instruct with hf-inference provider for text generation
6436cd9 -
Fix Together provider: use chat_completion instead of text_generation for conversational models
ca333e4 -
Add Qwen3-Next-80B model with Together provider and update InferenceClient to support multiple providers
e65f7af -
Fix provider name: change 'huggingface' to 'hf-inference' for InferenceClient
710113d -
Fix InferenceClient usage: use provider='huggingface' and api_key parameter as per documentation
a598199 -
Replace manual HTTP requests with InferenceClient for better reliability and error handling
c1c187b -
Update model IDs to use BlenderBot and DialoGPT-Medium as known working models
4f99f28 -
Update model IDs to use full namespace and add DialoGPT-Small as working alternative
90a07ce -
Fix model IDs to use correct Hugging Face Inference API identifiers
d54847c -
Simplify model configuration to use only basic models available via HF Inference API
cf9d931 -
Simplify model configuration to use only basic models available via HF Inference API
afc682f -
Fix case dropdown initialization - load cases for default dataset on startup
4dd13f7 -
Enhanced debugging for case loading - check dataset existence and case details
33a1102 -
Add debugging for case loading issue
5098bbb -
Add Select All for models and debug case loading
c42c189 -
Add dataset visibility configuration - only show nyc_taxi_small by default
a026fe5 -
Ensure Global Leaderboard shows same columns as Evaluate tab for consistency
51503ea -
Fix Global Leaderboard column ordering to match configuration
aadec84 -
Fix leaderboard column ordering to match configuration
3fc9598 -
Add debugging for case loading KeyError
be92fdf -
Fix case loading terminology - reference_sql is human-provided ground truth
ec202ea -
Reorder leaderboard columns with comprehensive display
9271fde -
Fix column mismatch in results DataFrame - add rank column
b62caf4 -
Add Model Ranking column to leaderboard display
8ddc24b -
Fix DatasetManager to handle different use case requirements
1853581 -
Fix DatasetManager to handle multi-use-case structure
e6b0a87 -
Fix missing headers configuration in UI config
7856952 -
Add Hugging Face Spaces YAML frontmatter to README
2018997 -
Resolve all merge conflicts - keep DataEngEval version
328cf71 -
Initial commit for DataEngEval
acd8e16
-
initial commit
Verified signature8438e88 -
Duplicate from demo-leaderboard-backend/leaderboard
Verified signatureCo-authored-by: Clémentine Fourrier <clefourrier@users.noreply.huggingface.co>75267e0
