Add Boris-2-Preview-1 to the base-model arena

Adds opencerebral/Boris-2-Preview-1 to the base-model arena.

Boris-2-Preview-1 is a 143.7M-parameter base model pretrained from scratch by OpenCerebral (52.5B tokens on one V100). It is currently #2 on the Open SLM Leaderboard (Index 27.91). Model card: https://huggingface.co/opencerebral/Boris-2-Preview-1

Changes, all in app.py and mirroring the existing Boris-1.3 base entries:
- BASE_MODEL_IDS / BASE_MODEL_DISPLAY: the new model
- MODEL_PARAMS: 143.7e6
- GEN_DEFAULTS: same sampling settings as Boris-1.3-125M (64 new tokens, temperature 0.8, top_p 0.95, repetition_penalty 1.1)
- MODEL_CONTEXT: 2048

Tested with the arena's own load and generate path (AutoTokenizer/AutoModelForCausalLM with trust_remote_code=True, float32, use_cache=False, plain-text prompt since the model has no chat template) on transformers 5.15. The custom code is plain PyTorch with no extra dependencies and generates without a KV cache, which matches the arena's use_cache=False.

Action Automated by Claude Code

app.py

@@ -64,6 +64,7 @@ BASE_MODEL_IDS: List[str] = [
     "HuggingFaceTB/SmolLM2-135M",
     "OpenCerebral/Boris-1.3-125M",
     "OpenCerebral/Boris-1.3-75M",
+    "opencerebral/Boris-2-Preview-1",
     "CodeSoft/sorbet-v2-25m",
     "fromziro/Er-Large-30M",
     "fromziro/Negative-v1.0",
@@ -82,6 +83,7 @@ BASE_MODEL_DISPLAY: Dict[str, str] = {
     "HuggingFaceTB/SmolLM2-135M": "SmolLM2-135M",
     "OpenCerebral/Boris-1.3-125M": "Boris-1.3-125M",
     "OpenCerebral/Boris-1.3-75M": "Boris-1.3-75M",
+    "opencerebral/Boris-2-Preview-1": "Boris-2-Preview-1",
     "CodeSoft/sorbet-v2-25m": "sorbet-v2-25m",
     "fromziro/Er-Large-30M": "Er-Large-30M",
     "fromziro/Negative-v1.0": "Negative-v1.0",
@@ -108,6 +110,7 @@ MODEL_PARAMS: Dict[str, float] = {
     "HuggingFaceTB/SmolLM2-135M": 135.0e6,
     "OpenCerebral/Boris-1.3-125M": 125.0e6,
     "OpenCerebral/Boris-1.3-75M": 75.0e6,
+    "opencerebral/Boris-2-Preview-1": 143.7e6,
     "CodeSoft/sorbet-v2-25m": 25.2e6,
     "fromziro/Er-Large-30M": 31.9e6,
     "fromziro/Negative-v1.0": 67.7e3,
@@ -205,6 +208,7 @@ GEN_DEFAULTS: Dict[str, dict] = {
     "OpenCerebral/Boris-1.3-75M-Instruct": {"max_new_tokens": 64, "temperature": 0.7, "top_p": 0.9, "repetition_penalty": 1.1, "do_sample": True},
     "OpenCerebral/Boris-1.3-125M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "OpenCerebral/Boris-1.3-75M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
+    "opencerebral/Boris-2-Preview-1": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "CodeSoft/sorbet-v2-25m": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "fromziro/Er-Large-30M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "fromziro/Negative-v1.0": {"max_new_tokens": 48, "temperature": 0.9, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
@@ -236,6 +240,7 @@ MODEL_CONTEXT: Dict[str, int] = {
     "OpenCerebral/Boris-1.3-75M-Instruct": 2048,
     "OpenCerebral/Boris-1.3-125M": 2048,
     "OpenCerebral/Boris-1.3-75M": 2048,
+    "opencerebral/Boris-2-Preview-1": 2048,
     "CodeSoft/sorbet-v2-25m": 4096,
     "fromziro/Er-Large-30M": 2048,
     "fromziro/Negative-v1.0": 96,