Spaces:
Running
Running
Add Apriel-1.5-15b-Thinker
Browse files
app.py
CHANGED
|
@@ -55,6 +55,11 @@ MODELS = {
|
|
| 55 |
# "description": "4-bit AWQ quantized dense causal language model with 32.8B total parameters (31.2B non-embedding), 64 layers, 64 query heads & 8 KV heads, native 32,768-token context (extendable to 131,072 via YaRN). Features seamless switching between thinking mode (for complex reasoning, math, coding) and non-thinking mode (for efficient dialogue), strong multilingual support (100+ languages), and leading open-source agent capabilities."
|
| 56 |
# },
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
# 14.8B total parameters
|
| 59 |
"Qwen3-14B": {
|
| 60 |
"repo_id": "Qwen/Qwen3-14B",
|
|
|
|
| 55 |
# "description": "4-bit AWQ quantized dense causal language model with 32.8B total parameters (31.2B non-embedding), 64 layers, 64 query heads & 8 KV heads, native 32,768-token context (extendable to 131,072 via YaRN). Features seamless switching between thinking mode (for complex reasoning, math, coding) and non-thinking mode (for efficient dialogue), strong multilingual support (100+ languages), and leading open-source agent capabilities."
|
| 56 |
# },
|
| 57 |
|
| 58 |
+
"Apriel-1.5-15b-Thinker": {
|
| 59 |
+
"repo_id": "ServiceNow-AI/Apriel-1.5-15b-Thinker",
|
| 60 |
+
"description": "Multimodal reasoning model with 15B parameters, trained via extensive mid-training on text and image data, and fine-tuned only on text (no image SFT). Achieves competitive performance on reasoning benchmarks like Artificial Analysis (score: 52), Tau2 Bench Telecom (68), and IFBench (62). Supports both text and image understanding, fits on a single GPU, and includes structured reasoning output with tool and function calling capabilities."
|
| 61 |
+
},
|
| 62 |
+
|
| 63 |
# 14.8B total parameters
|
| 64 |
"Qwen3-14B": {
|
| 65 |
"repo_id": "Qwen/Qwen3-14B",
|