Upload 8 files

.gitattributes

@@ -0,0 +1,2 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- ai-evaluation
+- mathematics
+- trigonometry
+- calculus
+- algebra
+- qwen2
+- causal-lm
+- trained-from-scratch
+base_model: none
+---
+
+# HyperNix.2
+
+**Version:** 0.2  
+**Parameters:** 101,370,880 (~101.37 M)  
+**Architecture:** Qwen 2.5-style decoder-only transformer (trained **from scratch**)  
+
+## What can it do?
+
+| Domain | Capability |
+|---|---|
+| AI Evaluation | Test, evaluate, grade and rate other AI model outputs |
+| Mathematics | Full Trigonometry, Calculus (limits/derivatives/integrals), Algebra 1 & 2 |
+| English | Fluent conversational English |
+
+## Architecture
+
+| Hyperparameter | Value |
+|---|---|
+| `vocab_size` | 151,936 (Qwen 2.5 tokenizer) |
+| `hidden_size` | 512 |
+| `intermediate_size` | 1,193 (SwiGLU) |
+| `num_hidden_layers` | 9 |
+| `num_attention_heads` | 8 |
+| `num_key_value_heads` | 4 (GQA) |
+| `max_position_embeddings` | 2,048 |
+| `tie_word_embeddings` | True |
+| Total parameters | **101,370,880** |
+
+## Training
+
+- Hardware: Single NVIDIA GTX 1080 (8 GB VRAM)
+- Precision: FP16 + gradient checkpointing
+- Optimizer: AdamW (lr=3e-4, cosine decay)
+- This is **not** a LoRA or fine-tune — all weights are randomly initialised and trained from scratch.
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("ray0rf1re/hyper-Nix.2")
+model     = AutoModelForCausalLM.from_pretrained("ray0rf1re/hyper-Nix.2", torch_dtype=torch.float16)
+
+prompt = "<|im_start|>user\nEvaluate this AI response: The capital of France is London.<|im_end|>\n<|im_start|>assistant\n"
+inputs = tokenizer(prompt, return_tensors="pt")
+with torch.no_grad():
+    out = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
+print(tokenizer.decode(out[0], skip_special_tokens=False))
+```

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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' }}
+{%- endif %}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1193,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 9,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.5.4",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3de485dbfafa5c3abed8c5f81a9f64ab8f067f2e321454c935f9a2c0d90a28e
+size 405532464

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_meta.json

@@ -0,0 +1,7 @@
+{
+  "step": 30000,
+  "loss": NaN,
+  "model_name": "HyperNix.2",
+  "version": "0.2",
+  "parameters": 101380096
+}