Spaces:
Sleeping
Sleeping
RGB Evaluation commited on
Commit ·
1b8d19d
1
Parent(s): ca5ddcb
feat: Add Moonshot Kimi K2 Instruct model to DEFAULT_MODELS
Browse files- Added moonshotai/kimi-k2-instruct to primary evaluation models
- Now evaluating with 5 models total
- Kimi K2 provides multi-lingual capabilities and strong reasoning
- Maintains all existing models in list
- src/config.py +2 -1
src/config.py
CHANGED
|
@@ -26,12 +26,13 @@ DATASET_URLS = {
|
|
| 26 |
"en_fact.json": "https://raw.githubusercontent.com/chen700564/RGB/main/data/en_fact.json",
|
| 27 |
}
|
| 28 |
|
| 29 |
-
# Default models to evaluate (first
|
| 30 |
DEFAULT_MODELS: List[str] = [
|
| 31 |
"meta-llama/llama-4-maverick-17b-128e-instruct", # Llama 4 Maverick 17B
|
| 32 |
"meta-llama/llama-prompt-guard-2-86m", # Llama Prompt Guard 2 86M
|
| 33 |
"llama-3.1-8b-instant", # Llama 3.1 8B - Fast
|
| 34 |
"openai/gpt-oss-120b", # GPT OSS 120B
|
|
|
|
| 35 |
]
|
| 36 |
|
| 37 |
# Additional available models
|
|
|
|
| 26 |
"en_fact.json": "https://raw.githubusercontent.com/chen700564/RGB/main/data/en_fact.json",
|
| 27 |
}
|
| 28 |
|
| 29 |
+
# Default models to evaluate (first 5 as primary)
|
| 30 |
DEFAULT_MODELS: List[str] = [
|
| 31 |
"meta-llama/llama-4-maverick-17b-128e-instruct", # Llama 4 Maverick 17B
|
| 32 |
"meta-llama/llama-prompt-guard-2-86m", # Llama Prompt Guard 2 86M
|
| 33 |
"llama-3.1-8b-instant", # Llama 3.1 8B - Fast
|
| 34 |
"openai/gpt-oss-120b", # GPT OSS 120B
|
| 35 |
+
"moonshotai/kimi-k2-instruct", # Moonshot Kimi K2 Instruct
|
| 36 |
]
|
| 37 |
|
| 38 |
# Additional available models
|