初始化项目，由ModelHub XC社区提供模型

Model: ray0rf1re/Nano-nano_v4.5 Source: Original Platform
2026-07-17 09:41:11 +08:00
commit 12583ebf3b
13 changed files with 250988 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+eval_category_scores.png filter=lfs diff=lfs merge=lfs -text
+training_curves.png filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,245 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- llama
+- causal-lm
+- text-generation
+- instruction-tuned
+- nano
+- v4.5
+- pytorch
+pipeline_tag: text-generation
+datasets:
+- Roman1111111/claude-opus-4.6-10000x
+- WithinUsAI/GPT5.5_thinking_max_distill_god_seed_25K
+- HuggingFaceH4/MATH-500
+- lighteval/MATH-Hard
+- garage-bAInd/Open-Platypus
+- nvidia/OpenCodeInstruct
+- iamtarun/python_code_instructions_18k_alpaca
+- b-mc2/sql-create-context
+- teknium/OpenHermes-2.5
+- ray0rf1re/FineWeb-Nano
+- tonytins/chat-dataset
+- Amod/mental_health_counseling_conversations
+- databricks/databricks-dolly-15k
+- mlabonne/guanaco-llama2-1k
+- fka/awesome-chatgpt-prompts
+- ray0rf1re/hyper-pip
+- HuggingFaceH4/ultrachat_200k
+model-index:
+- name: Nano-nano v4.5
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    metrics:
+    - name: Training Loss
+      type: loss
+      value: 5.1763
+    - name: Overall Eval Score
+      type: accuracy
+      value: 0.1667
+    - name: Knowledge
+      type: accuracy
+      value: 0
+    - name: Reasoning
+      type: accuracy
+      value: 0
+    - name: Hallucination Resistance
+      type: accuracy
+      value: 0
+    - name: Instruction Following
+      type: accuracy
+      value: 0.5
+    - name: Coherence
+      type: accuracy
+      value: 0.3333
+new_version: ray0rf1re/Nano-nano-4.6
+---
+
+<div align="center">
+
+# 🧠 Nano-nano v4.5
+
+### ~255.7 M · LLaMA · Instruction-tuned · From scratch
+
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Loss](https://img.shields.io/badge/Train_Loss-5.176-orange)](https://huggingface.co/ray0rf1re/Nano-nano_v4.5)
+[![Eval](https://img.shields.io/badge/Eval_Score-16%25-orange)](https://huggingface.co/ray0rf1re/Nano-nano_v4.5)
+[![Datasets](https://img.shields.io/badge/Datasets-15-blueviolet)](https://huggingface.co/ray0rf1re/Nano-nano_v4.5)
+
+Successor to [Nano-nano v4](ray0rf1re/Nano-nano-v4).  
+Same architecture family, **~8.5% larger**, trained from scratch on 15 carefully weighted datasets.
+
+</div>
+
+---
+
+## 📋 Quick Facts
+
+| | |
+|---|---|
+| Architecture | LLaMA (decoder-only) |
+| Parameters | ~255.7 M |
+| Context length | 2 048 tokens |
+| Vocabulary | 50,264 tokens |
+| Training loss | `5.1763` |
+| Eval score | `16.7%` |
+| Trained on | 0.08 B tokens |
+| Hardware | NVIDIA GTX 1080 8 GB (Pascal) |
+| Trained | 2026-05-09 22:50 |
+
+---
+
+## 🏗️ Architecture
+
+Standard LLaMA decoder-only transformer. Scaled **~8.5% wider + 1 extra layer** vs v4.
+
+| Hyperparameter | v4 | **v4.5** |
+|---|---|---|
+| Parameters | ~236 M | **~255.7 M** |
+| `hidden_size` | 896 | 896 |
+| `intermediate_size` | 2 688 | **2 912** |
+| `num_hidden_layers` | 14 | **15** |
+| `num_attention_heads` | 14 | 14 |
+| `num_key_value_heads` | 14 | 14 |
+| `head_dim` | 64 | 64 |
+| `vocab_size` | 50 264 | 50,264 |
+| `max_position_embeddings` | 1 024 | **2 048** |
+| `rms_norm_eps` | 1e-6 | 1e-6 |
+| `rope_theta` | 10 000 | 10 000 |
+| `hidden_act` | SiLU | SiLU |
+| `tie_word_embeddings` | False | False |
+| `attention_bias` | False | False |
+| `mlp_bias` | False | False |
+
+---
+
+## 📊 Evaluation
+
+Automatically evaluated after training across 5 capability dimensions.
+
+| Category | Hits | Score |
+|---|---|---|
+| Knowledge | 0/5 | 🔴 0% |
+| Reasoning | 0/4 | 🔴 0% |
+| Hallucination | 0/4 | 🔴 0% |
+| Instruction | 2/4 | 🟡 50% |
+| Coherence | 1/3 | 🔴 33% |
+| **Overall** | — | **🔴 17%** |
+
+> **Hallucination resistance** — whether the model appropriately declines questions
+> about future events, fictional entities, or impossible premises rather than confabulating.
+
+![Category Scores](eval_category_scores.png)
+![Hallucination](eval_hallucination.png)
+![Training Curves](training_curves.png)
+
+---
+
+## 🍳 Training
+
+| Setting | Value |
+|---|---|
+| Hardware | GTX 1080 8 GB · Pascal · CUDA 6.1 |
+| Precision | fp32 weights / fp16 AMP (GradScaler) |
+| Optimizer | StovetopCooker (HyperNix, pre-Volta) |
+| LR | `0.0001` cosine decay |
+| Warmup | 6% of steps |
+| Embedding freeze | First 15% of steps |
+| Effective batch | 8 × 2048 = 16,384 tokens/step |
+| Steps | 5092 |
+| Total tokens | 0.08 B |
+| Grad clipping | 1.0 |
+| Grad checkpointing | ✅ |
+| Peak VRAM | 5.34 GB |
+| HyperNix | ✅ `freezer` · `StovetopCooker` · `old_fridge` · `new_fridge` · `smoke_alarm` · `pans` · `smoker` |
+
+### Dataset Mix
+
+| Dataset | Samples | Weight | Category |
+|---|---|---|---|
+| `Roman1111111/claude-opus-4.6-10000x` | 10 k | 2.5× | Claude conversations |
+| `WithinUsAI/GPT5.5_thinking_max_distill_god_seed_25K` | 25 k | 2.0× | Reasoning / thinking |
+| `HuggingFaceH4/MATH-500` | 500 | 2.0× | Competition math |
+| `lighteval/MATH-Hard` | 10 k | 2.0× | Hard math |
+| `garage-bAInd/Open-Platypus` | 25 k | 1.8× | Reasoning instruction |
+| `iamtarun/python_code_instructions_18k_alpaca` | 8 k | 1.6× | Python code |
+| `b-mc2/sql-create-context` | 6 k | 1.4× | SQL code |
+| `nvidia/OpenCodeInstruct` | 30 k | 1.5× | Code instruction |
+| `teknium/OpenHermes-2.5` | 30 k | 1.5× | General instruction |
+| `Amod/mental_health_counseling_conversations` | 5 k | 1.2× | Chat / counseling |
+| `ray0rf1re/FineWeb-Nano` | 50 k | 1.0× | Web text |
+| `tonytins/chat-dataset` | 10 k | 1.0× | Conversation |
+| `databricks/databricks-dolly-15k` | 15 k | 1.0× | Instruction following |
+| `mlabonne/guanaco-llama2-1k` | 1 k | 1.0× | General QA |
+| `ray0rf1re/hyper-pip` | 20 k | 2.0× | HyperNix pip data |
+| `HuggingFaceH4/ultrachat_200k` | 30 k | 1.5× | Multi-turn chat |
+| `fka/awesome-chatgpt-prompts` | 5 k | 0.8× | Prompt engineering |
+
+---
+
+## 🚀 Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "ray0rf1re/Nano-nano_v4.5",
+    torch_dtype="auto",
+    device_map="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained("ray0rf1re/Nano-nano_v4.5")
+
+def generate(prompt: str, max_new_tokens: int = 256) -> str:
+    text   = f"### Instruction:
+{prompt}
+
+### Response:
+"
+    inputs = tokenizer(text, return_tensors="pt").to(model.device)
+    out    = model.generate(
+        **inputs,
+        max_new_tokens  = max_new_tokens,
+        do_sample       = True,
+        temperature     = 0.7,
+        top_p           = 0.9,
+        repetition_penalty = 1.1,
+        pad_token_id    = tokenizer.eos_token_id,
+    )
+    new_ids = out[0][inputs["input_ids"].shape[-1]:]
+    return tokenizer.decode(new_ids, skip_special_tokens=True).strip()
+
+# Examples
+print(generate("Write a Python function to reverse a linked list."))
+print(generate("What is the capital of France?"))
+print(generate("Explain gradient descent in simple terms."))
+```
+
+---
+
+## ⚠️ Limitations
+
+- Context limited to **1 024 tokens** — unsuitable for long documents
+- Trained on **0.08 B tokens** — far less than production models
+- May hallucinate on obscure or out-of-distribution queries
+- Not RLHF/DPO aligned — outputs may vary in safety and tone
+- Pascal GPU constraint (GTX 1080): fp32/fp16 only, no bf16
+
+---
+
+## 📜 Citation
+
+```bibtex
+@misc{nano-nano-v45,
+  author       = {ray0rf1re},
+  title        = {Nano-nano v4.5: Compact LLaMA-Family Causal LM},
+  year         = {2026},
+  publisher    = {HuggingFace},
+  howpublished = {https://huggingface.co/ray0rf1re/Nano-nano_v4.5},
+}
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "eos_token_id": 50256,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 2912,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 15,
+  "num_key_value_heads": 14,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "factor": 2.0,
+    "rope_theta": 10000.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 50264
+}
--- a/eval_category_scores.png
+++ b/eval_category_scores.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386d28a4231d6844c9af71625df1b3ebb8695ac85ecd08fd330d7258d19e86a5
+size 146081
--- a/eval_hallucination.png
+++ b/eval_hallucination.png
--- a/eval_results.json
+++ b/eval_results.json
@@ -0,0 +1,239 @@
+{
+  "model": "ray0rf1re/Nano-nano_v4.5",
+  "eval_timestamp": "2026-05-10T07:21:48.937710",
+  "categories": {
+    "knowledge": {
+      "score": 0.0,
+      "hits": 0,
+      "total": 5,
+      "details": [
+        {
+          "prompt": "Who wrote Romeo and Juliet?",
+          "response": "SELECT COUNT(7,4,4)$3,4=2)\n4.5)$\n2.4 = 1.4 + 8 + 3\n\n2.5=2+4+4) + 1.5) + 3 + 1.2 + 1,4.4)\n2.5+2.4)\n5.5 = x=3.4) \\frac{2.4.2 \\frac{5}{4.5}$\\sqrt{8}$.7.7.4$\n2.4)\n2.5.3+",
+          "passed": false,
+          "expected": [
+            "shakespeare",
+            "william shakespeare"
+          ]
+        },
+        {
+          "prompt": "What is the speed of light in m/s?",
+          "response": "SELECT COUNT(6,5) + 1x^2)$n\n2.5 + 4x^4 + 1,3x^2 -5+5 - 1+5 + 1,2) = 1)$\\frac{3 - 1}\n\\frac{(x+1}{4) \\frac{1}{5}^4^2+2+4+3+1,1 - 1 \\frac{2}{4}$\n\\[\\circ_4 + \\le= 1$ and the square numbers to the sum of $x^2 = 4x^4",
+          "passed": false,
+          "expected": [
+            "299792458",
+            "3e8",
+            "3 \u00d7 10"
+          ]
+        },
+        {
+          "prompt": "What is the capital of France?",
+          "response": "SELECT COUNT(4,4) FROM table_2 ON T1.5) FROM table_4_4 WHERE name_3.5\",4.7+4.4.4\\n\".$\n4.7.4.5,4)^2.4.4.4.4+2.4.85,2.8)\n2.4.5.2.4.5.8)\n2.5.5.4.5.4.4.4-4)\n4.3.4 = 1.3 + 1.5,3.",
+          "passed": false,
+          "expected": [
+            "paris"
+          ]
+        },
+        {
+          "prompt": "What element has atomic number 79?",
+          "response": "SELECT COUNT(2) FROM table_4 WHERE is a new total in the sum of the given points by the first?\n\ndef sum of the given list of the probability of the same equation in the number of the two order of the two?",
+          "passed": false,
+          "expected": [
+            "gold",
+            "au"
+          ]
+        },
+        {
+          "prompt": "In what year did World War II end?",
+          "response": "SELECT COUNT(8,2),4,4,4));\n\\[0,3,4,4,1));\n\n\n\n\n#3;\n\n3,4,4,4,4,3));\ndraw((4,4,4,2,4,4,4,4,4));\n\ndraw((5,4,5,5,2,4,3,4,5,4));\ndraw((1,5,2,4,3,4,4,2,4,2,2,4,3));\ndot((1",
+          "passed": false,
+          "expected": [
+            "1945"
+          ]
+        }
+      ]
+    },
+    "reasoning": {
+      "score": 0.0,
+      "hits": 0,
+      "total": 4,
+      "details": [
+        {
+          "prompt": "If a train travels 60 mph for 2.5 hours, how far does it travel?",
+          "response": "5.5x1.5,2,4.5)4.4.5.4-4+4.5+5+5+4)\n4.5.3.8 \\right\\n7.4.3)\n4.8.4.4.3+4.3.4)3.4 -4.4.4)\n4.5.5).4.8^4.4+4+4)\n5.4.4=3.4,5.4+4-4+5)\n5.4.9.4-",
+          "passed": false,
+          "expected": [
+            "150"
+          ]
+        },
+        {
+          "prompt": "What comes next in the sequence: 2, 4, 8, 16, ?",
+          "response": "SELECT COUNT(0,2,4,2,1,4,5));\n\ndraw((2,2,3,4,4,5,4,2,4,1));\ndraw((2,4,4,4,4,3)--(1,2,3,4,4,2,1,4,4,4,4,4,2,5,2,5,5,2,4));\n\n[/asy,4,4,4,2,2,4,4,2,2,5,4,4,2,2",
+          "passed": false,
+          "expected": [
+            "32"
+          ]
+        },
+        {
+          "prompt": "A bat and ball cost $1.10. The bat costs $1 more than the ball. How much does the ball cost?",
+          "response": "3.7 + 2.4.4 -2.7 + 1.5.4-3.4)\n4.4.5-4.4+4)\n3.5$.4)\n4.4.5)\n2.5.4-3.4+4,4.4=2.4)\n4.3.4.5 + 0.4+4)\n4.4.4.4)3+3)\n4.4.5\\3+4$3+5+4.4,4)\n\\n-4 +2",
+          "passed": false,
+          "expected": [
+            "0.05",
+            "5 cents",
+            "five cents"
+          ]
+        },
+        {
+          "prompt": "If all bloops are razzles and all razzles are lazzles, are all bloops lazzles?",
+          "response": "2.5,1.5,1,4.4,4,4,4,3)--5));\n2.5.5,4.5));\n3.5,3.7.4,3,4)--5,4.5));\n2.5.5.5));\n5.3.5.5/4.4 +3,3,3,4)--(2.4)3.5));\n5.8.7+4,4.4.4)\n3.5.8/4.4.5.7+2.4",
+          "passed": false,
+          "expected": [
+            "yes"
+          ]
+        }
+      ]
+    },
+    "hallucination": {
+      "score": 0.0,
+      "hits": 0,
+      "total": 4,
+      "details": [
+        {
+          "prompt": "Who won the 2031 FIFA World Cup?",
+          "response": "SELECT COUNT(*) FROM table_4 WHERE product_4 = \"I\"\"\" AND\" AND\"\nprint(f\"Example\"Ced_id for \"2.5\",\n2.2.2f\"  # In3.5\",",
+          "passed": false,
+          "expected": [
+            "don't know",
+            "cannot",
+            "do not know",
+            "unsure",
+            "no information",
+            "future",
+            "2031",
+            "haven't",
+            "have not"
+          ]
+        },
+        {
+          "prompt": "What is the capital of the fictional country Zandoria?",
+          "response": "SELECT COUNT(5,3)+4.2+2.4));\n4.4+5.8^5\\n5+5)=1.4+5+1)2.5 \\frac{3)$\n2.4)\n4.5+2=2.5}4.4^4+3+4+2+4+5+5)4+4+5)^4+3+4+5+3+5+1+2+2+4+5+2+4+3+4+1$\",(5+",
+          "passed": false,
+          "expected": [
+            "don't know",
+            "fictional",
+            "not real",
+            "doesn't exist",
+            "does not exist",
+            "made up",
+            "no such"
+          ]
+        },
+        {
+          "prompt": "What did Einstein say in his 1987 speech?",
+          "response": "SELECT COUNT(5,5) = 1,4,2)$2,4,2,4,3,4,5,3,3,4,3,2,4,4,4,4,4));\n4\n5,4,4,4,4,5,4,4));\n3,2,4,4,4,5,5,4,5,4,4,2,3,4,2,5,4,4,4,3,4,5,3,4,3,4,5,2,8,",
+          "passed": false,
+          "expected": [
+            "1955",
+            "died",
+            "death",
+            "don't know",
+            "cannot",
+            "1879"
+          ]
+        },
+        {
+          "prompt": "Tell me about the moon landing on Mars in 1969.",
+          "response": "SELECT COUNT(n):",
+          "passed": false,
+          "expected": [
+            "moon",
+            "apollo",
+            "not mars",
+            "earth",
+            "don't know",
+            "incorrect",
+            "actually"
+          ]
+        }
+      ]
+    },
+    "instruction": {
+      "score": 0.5,
+      "hits": 2,
+      "total": 4,
+      "details": [
+        {
+          "prompt": "List exactly 3 prime numbers.",
+          "response": "SELECT COUNT(*) FROM table_name, 2,5,4,4,4,4,4)$",
+          "passed": true,
+          "expected": [
+            "2",
+            "3",
+            "5",
+            "7",
+            "11",
+            "13"
+          ]
+        },
+        {
+          "prompt": "Translate 'hello' to Spanish.",
+          "response": "from pathlib import Path\nfrom hypernix.sink import Sink\n\ns = Path(\"roted.txt\").write_text(\n    \"The quick brown fox\"",
+          "passed": false,
+          "expected": [
+            "hola"
+          ]
+        },
+        {
+          "prompt": "Write a haiku about rain.",
+          "response": "def calculate_id(2, x2):",
+          "passed": true,
+          "expected": []
+        },
+        {
+          "prompt": "What is 17 \u00d7 13?",
+          "response": "SELECT COUNT(x-4) + 5x^4 -3) = 3 + 1 = x + 8 + 1$-4^4^4) + \\frac{1}{4} + 3^4^4 + 1 + 1^4 + \\frac{n + 1 + 1 + 1 - 2^5x^4^4 + x^2 + 5x^4 - 1 + 3 + 8^4 + x + 2^2 - 0 + 1^5 + \\frac{1 - 1^2 + 1 + 1x^2 + 1 - 1 + x + 1.$",
+          "passed": false,
+          "expected": [
+            "221"
+          ]
+        }
+      ]
+    },
+    "coherence": {
+      "score": 0.3333333333333333,
+      "hits": 1,
+      "total": 3,
+      "details": [
+        {
+          "prompt": "Continue this sentence: The sun rises in the",
+          "response": "SELECT COUNT(5,2,4,4)2,4,2,5,3,4,4,3,4,4,4)--(4));\n5,2,2,4,4,4,4,3,1),7)--(1,4,2,4,2,1,4,3,1,5,2,4),2.5,2,4,3,2,5,4,1,5,3,2,4,2,2,1,3,4,5,4,4,4,4",
+          "passed": false,
+          "expected": [
+            "east",
+            "morning"
+          ]
+        },
+        {
+          "prompt": "What do plants need to perform photosynthesis?",
+          "response": "SELECT COUNT(nix.5.5+4,4)3+3+2+4+3+4+4+4+4+3+3+4+4+5+4+4,4x5+5+4+4+5+4+5+3+4+4+1+4=4-4+4+5+3+3+5+5+5+4+5-3$.4+4+2+4+5+4+5-5+4+5+4=2\\4+4+4+4",
+          "passed": false,
+          "expected": [
+            "light",
+            "sun",
+            "water",
+            "co2",
+            "carbon"
+          ]
+        },
+        {
+          "prompt": "Write one sentence about dogs.",
+          "response": "def is a long-3, 0.4) + 3-4.4,4,4,4) + 3 + (2.4,5) = 8\n5.5)^2) = 2.5\n4 = (2.4)\n3.5 + 4^4 -4 + 3.4,\\x^4.5\\n \\frac{1}{3}$\\3$\n2.4$\\sqrt{3}{4.2}= \\frac{4}=\\n$\\frac{3}{2}$ $x^2^",
+          "passed": true,
+          "expected": []
+        }
+      ]
+    }
+  },
+  "overall_score": 0.16666666666666666
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.7.0",
+  "use_cache": true
+}
--- a/loss_curve.png
+++ b/loss_curve.png
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b887221af7f01683fc5857df89e9bd8441abf4b087ec5bff9b315b3bb0ee1834
+size 1022742016
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<think>",
+    "</think>",
+    "<tool_call>",
+    "</tool_call>",
+    "<tool_response>",
+    "</tool_response>",
+    "<pad>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": 256,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c54996fd7a65dad74ebd6a138de87c0cbac5d00c4708b1c042eaaf07ef50c1
+size 5265
--- a/training_curves.png
+++ b/training_curves.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a125adc2bb94660ecd5110d47c59cfb5e1b180b4abe3bfb3e955538a9f098606
+size 123313