Update README.md

README.md

@@ -1,3 +1,194 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- crownelius/Opus-4.6-Reasoning-3300x
+base_model:
+- microsoft/phi-2
+- venkycs/phi-2-instruct
+pipeline_tag: text-generation
+---
+**LBNET-2.7B-BASE model card**
+
+We introduce the first-ever Logic/Reasoning-based transformer model based on Phi-2.
+In February 2026, we created an experimental architecture called LBNets, an attempt to inject reasoning-like layers into a model's architecture. In this case, we experimented with Phi-2.
+
+**Here is the logic behind LBNET-2.7B-BASE:**
+- Split the base model into two halves: pre-reasoning and post-reasoning layers.
+- Between these layers, you insert:
+      - learnable latent 'reasoning tokens'
+      - reasoning blocks (cross-attention: latent tokens attend to the main hidden states (the “context”), self-attention: latent tokens attend to each other, MLP)
+      - reasoning injector back into the main stream
+
+To make generation workable:
+- During prefill (the initial prompt, past_length == 0 and seq_len > 1), the model runs the reasoning loop once.
+- During token-by-token generation with KV-cache (seq_len == 1), the model skips the reasoning loop (otherwise it gets slow and unstable).
+
+LBNETS-2.7B-BASE achieves much above average benchmarks for its size compared to other models:
+
+|    Tasks    |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|-------------|------:|------|-----:|--------|---|-----:|---|-----:|
+|arc_challenge|      1|none  |     0|acc     |↑  |0.5324|±  |0.0146|
+|             |       |none  |     0|acc_norm|↑  |0.5478|±  |0.0145|
+|arc_easy     |      1|none  |     0|acc     |↑  |0.8047|±  |0.0081|
+|             |       |none  |     0|acc_norm|↑  |0.7862|±  |0.0084|
+|boolq        |      2|none  |     0|acc     |↑  |0.8346|±  |0.0065|
+|openbookqa   |      1|none  |     0|acc     |↑  |0.4040|±  |0.0220|
+|             |       |none  |     0|acc_norm|↑  |0.5160|±  |0.0224|
+|piqa         |      1|none  |     0|acc     |↑  |0.7889|±  |0.0095|
+|             |       |none  |     0|acc_norm|↑  |0.7949|±  |0.0094|
+|winogrande   |      1|none  |     0|acc     |↑  |0.7577|±  |0.0120|
+
+We reccommend running this model on at least an RTX 3050 with 8gb of VRAM.
+FOR FULL MODEL FUNCTIONALITY, YOU MUST USE THE CHAT SCRIPT BELOW:
+
+The script is ROCm-friendly. May need tweaking for CUDA setups.
+
+'''python
+
+import os
+import argparse
+import torch
+from transformers import AutoTokenizer
+
+from configuration import PhiReasoningConfig
+from modeling import PhiForLogicalReasoning
+
+# ROCm allocator hint (helps fragmentation on AMD ROCm)
+os.environ.setdefault("PYTORCH_HIP_ALLOC_CONF", "expandable_segments:True,max_split_size_mb:64")
+
+DEFAULT_SYSTEM_PROMPT = "You are LBNets, a helpful assistant."
+
+
+def format_prompt(system_prompt: str, user_text: str, history, max_turns: int = 6) -> str:
+    """
+    Build a single instruction that includes recent chat history.
+    This keeps compatibility with your training template.
+
+    history: list of (user, assistant) tuples
+    """
+    system_prompt = (system_prompt or "").strip()
+    user_text = (user_text or "").strip()
+
+    convo = ""
+    for u, a in history[-max_turns:]:
+        convo += f"User: {u}\nAssistant: {a}\n"
+
+    instruction = ""
+    if convo:
+        instruction += "Conversation so far:\n" + convo + "\n"
+    instruction += "Current user message:\n" + user_text
+
+    return (
+        f"### System:\n{system_prompt}\n\n"
+        f"### Instruction:\n{instruction}\n\n"
+        f"### Response:\n"
+    )
+
+
+@torch.inference_mode()
+def generate_text(model, tok, prompt_text: str, device: str, max_new_tokens: int = 256) -> str:
+    inputs = tok(
+        prompt_text,
+        return_tensors="pt",
+        add_special_tokens=False,
+        truncation=True,
+        max_length=768,  # history makes prompts longer; keep sane
+    ).to(device)
+
+    in_len = inputs["input_ids"].shape[1]
+
+    out_ids = model.generate(
+        **inputs,
+        do_sample=False,          # greedy
+        use_cache=True,           # KV cache (fast)
+        max_new_tokens=max_new_tokens,
+        min_new_tokens=1,
+
+        # general anti-loop controls (not per-problem patching)
+        repetition_penalty=1.10,
+        no_repeat_ngram_size=3,
+
+        pad_token_id=tok.pad_token_id,
+        eos_token_id=tok.eos_token_id,
+    )
+
+    new_ids = out_ids[0][in_len:]
+    text = tok.decode(new_ids, skip_special_tokens=True)
+
+    # Avoid "blank" replies from leading newline spam
+    return text.lstrip("\n").rstrip()
+
+
+def load_model(model_path: str, device: str):
+    cfg = PhiReasoningConfig.from_pretrained(model_path)
+    cfg.attn_implementation = "eager"
+    cfg.use_cache = True
+
+    tok = AutoTokenizer.from_pretrained(model_path)
+    if tok.pad_token is None:
+        tok.pad_token = tok.eos_token
+        tok.pad_token_id = tok.eos_token_id
+
+    model = PhiForLogicalReasoning.from_pretrained(
+        model_path,
+        config=cfg,
+        torch_dtype=torch.float16,   # often faster/more compatible on ROCm than bf16
+        low_cpu_mem_usage=True,
+    ).to(device)
+
+    model.eval()
+
+    gate = model.model.reasoning_injector.gate_scale.detach().float().cpu().numpy()
+    total_params = sum(p.numel() for p in model.parameters())
+    print(f"Loaded: {model_path}")
+    print(f"Parameters: {total_params:,}")
+    print(f"Gate scale: {gate}")
+    print(f"Device: {device}")
+
+    return model, tok
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--model_path", default="./outputs/phi-reasoning-crownelius-opus")
+    ap.add_argument("--device", default="cuda:0")
+    ap.add_argument("--system_prompt", default=DEFAULT_SYSTEM_PROMPT)
+    ap.add_argument("--max_new_tokens", type=int, default=256)
+    ap.add_argument("--history_turns", type=int, default=6)
+    args = ap.parse_args()
+
+    model, tok = load_model(args.model_path, args.device)
+
+    history = []
+
+    print("\n============================================================")
+    print("LBNets Chat Ready!")
+    print("Commands: 'quit' to exit | 'reset' to clear conversation")
+    print("============================================================\n")
+
+    while True:
+        user = input("User: ").strip()
+        if not user:
+            continue
+
+        if user.lower() in ("quit", "exit", "q"):
+            break
+
+        if user.lower() in ("reset", "/reset"):
+            history.clear()
+            print("AI: Conversation reset.\n")
+            continue
+
+        prompt = format_prompt(args.system_prompt, user, history, max_turns=args.history_turns)
+        resp = generate_text(model, tok, prompt, args.device, max_new_tokens=args.max_new_tokens)
+
+        print(f"AI: {resp}\n")
+
+        # store turn
+        history.append((user, resp))
+
+
+if __name__ == "__main__":
+    main()
+'''
+