Add wayneworkman2012/peacebell-v1-148M (WWII domain model, greedy; additive Peacebell-only branch)

app.py

@@ -39,6 +39,7 @@ MODEL_IDS: List[str] = [
     "BananaMind/BananaMind-2-Pro-Preview-Chat",
     "BananaMind/BananaMind-2-Nano-Chat",
     "BananaMind/BananaMind-2-Mini-Chat",
+    "wayneworkman2012/peacebell-v1-148M",
 ]
 
 MODEL_DISPLAY: Dict[str, str] = {
@@ -53,6 +54,7 @@ MODEL_DISPLAY: Dict[str, str] = {
     "BananaMind/BananaMind-2-Pro-Preview-Chat": "BananaMind-2-Pro-Preview-Chat",
     "BananaMind/BananaMind-2-Nano-Chat": "BananaMind-2-Nano-Chat",
     "BananaMind/BananaMind-2-Mini-Chat": "BananaMind-2-Mini-Chat",
+    "wayneworkman2012/peacebell-v1-148M": "peacebell-v1-148M",
 }
 
 BASE_MODEL_IDS: List[str] = [
@@ -121,6 +123,7 @@ MODEL_PARAMS: Dict[str, float] = {
     "DedeProGames/Kiyo-230M-Preview": 229.7e6,
     "DedeProGames/Kiyo-135M": 134.5e6,
     "DedeProGames/Kiyo-65M": 65.0e6,
+    "wayneworkman2012/peacebell-v1-148M": 148.55e6,
 }
 
 FALLBACK_IDS: Dict[str, str] = {}
@@ -218,6 +221,8 @@ GEN_DEFAULTS: Dict[str, dict] = {
     "DedeProGames/Kiyo-230M-Preview": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "DedeProGames/Kiyo-135M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
     "DedeProGames/Kiyo-65M": {"max_new_tokens": 64, "temperature": 0.8, "top_p": 0.95, "repetition_penalty": 1.1, "do_sample": True},
+    # Peacebell: greedy (temperature 0), no repetition penalty, no n-gram block; decoded by its own ChatML path (generate_peacebell)
+    "wayneworkman2012/peacebell-v1-148M": {"max_new_tokens": 64, "temperature": 0.0, "do_sample": False, "repetition_penalty": 1.0},
 }
 
 MODEL_CONTEXT: Dict[str, int] = {
@@ -248,6 +253,7 @@ MODEL_CONTEXT: Dict[str, int] = {
     "DedeProGames/Kiyo-230M-Preview": 2048,
     "DedeProGames/Kiyo-135M": 8192,
     "DedeProGames/Kiyo-65M": 2048,
+    "wayneworkman2012/peacebell-v1-148M": 16384,
 }
 
 
@@ -894,6 +900,18 @@ def build_inputs(tokenizer, model_id: str, prompt: str):
 def is_diffusion_model(model_id: str) -> bool:
     return "metadiffusion" in model_id.lower()
 
+def is_peacebell_model(model_id: str) -> bool:
+    return model_id.lower().startswith("wayneworkman2012/peacebell-")
+
+def generate_peacebell(model, tokenizer, prompt: str, max_new: int) -> str:
+    """Peacebell ships its own ChatML encoder + KV-cached greedy decoder (no HF generate(), no Jinja chat_template):
+    special-token ids are injected by id exactly as at training time. Same path as its demo Space. Temperature 0."""
+    ids = tokenizer.build_chatml_ids([{"role": "user", "content": prompt}], add_generation_prompt=True)
+    input_ids = torch.tensor(ids, dtype=torch.long, device=DEVICE)
+    out_ids = model.chat_generate(input_ids, max_new_tokens=int(max_new), temperature=0.0, no_repeat_ngram_size=0)
+    text = tokenizer.decode_response(out_ids)
+    return text if text else "[Empty response]"
+
 def generate_for_model(model_id: str, prompt: str, max_new_tokens: int = 0) -> str:
     ensure_models_loaded()
     if model_id not in models or model_id not in tokenizers:
@@ -910,6 +928,8 @@ def generate_for_model(model_id: str, prompt: str, max_new_tokens: int = 0) -> s
     try:
         if is_diffusion_model(model_id):
             return generate_diffusion(model, tokenizer, prompt, cfg)  # type: ignore
+        if is_peacebell_model(model_id):
+            return generate_peacebell(model, tokenizer, prompt, max_new)
         inputs = build_inputs(tokenizer, model_id, prompt)
         input_len = inputs["input_ids"].shape[1]
         gen_kwargs = {

requirements.txt

@@ -7,4 +7,5 @@ huggingface_hub==1.22.0
 accelerate==1.14.0
 numpy==2.2.6
 plotly>=5.18.0
-tiktoken>=0.8.0
+tiktoken>=0.8.0
+sentencepiece>=0.2.0