Initial upload: KnowForge-0.6B

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.7.0"
+}

inference.py

@@ -0,0 +1,121 @@
+"""
+KnowForge-0.6B inference — standalone, no extra deps beyond transformers.
+
+CLI:   python inference.py "ZELPH RULES: ... Question: ..."
+API:   from inference import ask; result = ask("ZELPH RULES: ...")
+"""
+import re
+import sys
+from pathlib import Path
+from typing import Optional
+
+_MODEL_DIR = Path(__file__).parent
+_pipeline  = None  # lazy singleton
+
+
+def _load_pipeline():
+    global _pipeline
+    if _pipeline is not None:
+        return _pipeline
+    import torch
+    from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+    tokenizer = AutoTokenizer.from_pretrained(str(_MODEL_DIR), trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        str(_MODEL_DIR),
+        dtype=torch.float16,
+        device_map="auto",
+        trust_remote_code=True,
+    )
+    model.eval()
+    _pipeline = pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+    )
+    return _pipeline
+
+
+def _split_think(raw: str) -> tuple[str, str]:
+    """Split <think>...</think> from final answer. Returns (answer, reasoning).
+
+    Handles truncated output where </think> was never generated.
+    """
+    closed_match = re.search(r"<think>(.*?)</think>", raw, re.DOTALL)
+    if closed_match:
+        reasoning = closed_match.group(1).strip()
+        answer = re.sub(r"<think>.*?</think>", "", raw, flags=re.DOTALL).strip()
+        return answer, reasoning
+
+    # Unclosed <think> block — generation was cut off during reasoning
+    open_match = re.search(r"<think>(.*)", raw, re.DOTALL)
+    if open_match:
+        return "", open_match.group(1).strip()
+
+    return raw.strip(), ""
+
+
+def ask(
+    prompt: str,
+    max_new_tokens: int = 512,
+    temperature: float = 0.0,
+    do_sample: bool = False,
+) -> dict:
+    """
+    Run a KnowForge prompt through the model.
+
+    Args:
+        prompt: Full user-turn text, e.g. "ZELPH RULES: ... Question: ..."
+        max_new_tokens: Max tokens to generate.
+        temperature: Sampling temperature (ignored when do_sample=False).
+        do_sample: Enable sampling; set True + temperature>0 for stochastic output.
+
+    Returns:
+        {
+            "answer":    str  — text after </think> (or full output if no think block),
+            "reasoning": str  — text inside <think>...</think>, empty string if absent,
+        }
+    """
+    pipe = _load_pipeline()
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are given rules for a fictional system that does NOT exist in the "
+                "real world. Reason STRICTLY from the rules provided. Do NOT use any "
+                "outside knowledge. Show your reasoning inside <think>...</think> tags "
+                "before giving your final answer."
+            ),
+        },
+        {"role": "user", "content": prompt},
+    ]
+
+    gen_kwargs: dict = {
+        "max_new_tokens": max_new_tokens,
+        "do_sample": do_sample,
+        "pad_token_id": pipe.tokenizer.eos_token_id,
+    }
+    if do_sample:
+        gen_kwargs["temperature"] = temperature
+
+    outputs = pipe(messages, **gen_kwargs)
+
+    raw = outputs[0]["generated_text"][-1]["content"]
+    answer, reasoning = _split_think(raw)
+    return {"answer": answer, "reasoning": reasoning}
+
+
+def _main():
+    if len(sys.argv) < 2:
+        print("Usage: python inference.py \"ZELPH RULES: ... Question: ...\"")
+        sys.exit(1)
+    prompt = " ".join(sys.argv[1:])
+    result = ask(prompt)
+    print("Answer:", result["answer"])
+    if result["reasoning"]:
+        print("\nReasoning:")
+        print(result["reasoning"])
+
+
+if __name__ == "__main__":
+    _main()

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c96242a425432dea030658e7e1624ebbd95ba3bb9cb0f14ffa4829e48230a3
+size 1192135096

requirements.txt

@@ -0,0 +1,3 @@
+torch>=2.0.0
+transformers>=4.40.0
+accelerate>=0.27.0

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}