Upload 2 files

README.md

@@ -1,3 +1,73 @@
----
-license: apache-2.0
----
+---
+language: multilingual
+license: apache-2.0
+author: DarkPs
+library_name: transformers
+tags:
+  - ice-ai
+  - ice-0001
+  - text-generation
+  - conversational
+  - programming
+pipeline_tag: text-generation
+---
+
+# ICE 0001
+
+The "ice" model is a very robust, medium-sized model for human-like conversations, designed for quick chats and small code snippets.
+---
+
+The ice model was released with massive equations:
+
+### Major Improvements
+
+* It was trained on 5.47 billion Codex conversations.
+* It was also trained on more than 30 billion human conversations to better adapt to different Arabic dialects and multiple languages.
+
+---
+
+# Key Specifications
+
+* **Model Family:** ICE AI
+* **ID:** ice-0001
+* **Model Size:** 8B Parameters
+* **Context Length:** 32,768 tokens
+* **Format:** Transformers
+* **Inference Support:** CPU / GPU
+* **Primary Focus:** Human-like conversational AI
+
+### Training
+
+Trained on approximately **36 trillion tokens** across **119 languages and dialects**, with a strong focus on multiple Arabic dialects, international languages, and programming/code data.
+
+---
+
+# Recommended Usage
+
+ICE AI performs best when used for:
+
+* General conversations
+* multilingual chat
+* Software development
+* Code generation
+* Code debugging
+* Technical questions
+* Scripting and automation
+* Local offline AI deployment
+
+---
+
+# ⚠️ Notes
+
+* Designed for conversational and coding tasks.
+* Output quality may vary depending on the quantization level and hardware.
+* Best results are achieved with structured prompts.
+* Larger context sizes may require substantial RAM/VRAM.
+
+---
+
+# About Dark
+
+DarkPs is an AI organization owned by FanuonAI, developing and maintaining open-source AI models such as DarkIT, ICE AI, and DarkCoder.
+
+**Platform:** https://dark.ps

notebook.ipynb

@@ -0,0 +1,102 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "!pip install transformers accelerate torch huggingface_hub\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from huggingface_hub import HfApi\n",
+        "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
+        "import torch\n",
+        "\n",
+        "ИДЕНТИФИКАТОР_РЕПО = \"darkps/ice-AI-transformers\"\n",
+        "\n",
+        "АПИ = HfApi()\n",
+        "\n",
+        "СПИСОК_ФАЙЛОВ = АПИ.list_repo_files(ИДЕНТИФИКАТОР_РЕПО)\n",
+        "\n",
+        "print(\"Файлы репозитория:\")\n",
+        "for файл in СПИСОК_ФАЙЛОВ:\n",
+        "    print(файл)\n",
+        "\n",
+        "ТОКЕНИЗАТОР = AutoTokenizer.from_pretrained(\n",
+        "    ИДЕНТИФИКАТОР_РЕПО,\n",
+        "    trust_remote_code=True\n",
+        ")\n",
+        "\n",
+        "МОДЕЛЬ = AutoModelForCausalLM.from_pretrained(\n",
+        "    ИДЕНТИФИКАТОР_РЕПО,\n",
+        "    torch_dtype=torch.float16,\n",
+        "    device_map=\"auto\",\n",
+        "    trust_remote_code=True\n",
+        ")\n",
+        "\n",
+        "МОДЕЛЬ.eval()\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ЗАПРОС = \"Привет, как у тебя дела?\"\n",
+        "\n",
+        "СООБЩЕНИЯ = [\n",
+        "    {\n",
+        "        \"role\": \"user\",\n",
+        "        \"content\": ЗАПРОС\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "ТЕКСТ = ТОКЕНИЗАТОР.apply_chat_template(\n",
+        "    СООБЩЕНИЯ,\n",
+        "    tokenize=False,\n",
+        "    add_generation_prompt=True\n",
+        ")\n",
+        "\n",
+        "ВХОДЫ = ТОКЕНИЗАТОР(\n",
+        "    ТЕКСТ,\n",
+        "    return_tensors=\"pt\"\n",
+        ").to(МОДЕЛЬ.device)\n",
+        "\n",
+        "with torch.no_grad():\n",
+        "    ОТВЕТЫ = МОДЕЛЬ.generate(\n",
+        "        **ВХОДЫ,\n",
+        "        max_new_tokens=128,\n",
+        "        temperature=0.7,\n",
+        "        top_p=0.8,\n",
+        "        top_k=20,\n",
+        "        do_sample=True,\n",
+        "        eos_token_id=ТОКЕНИЗАТОР.eos_token_id\n",
+        "    )\n",
+        "\n",
+        "ОТВЕТ = ТОКЕНИЗАТОР.decode(\n",
+        "    ОТВЕТЫ[0][ВХОДЫ.input_ids.shape[-1]:],\n",
+        "    skip_special_tokens=True\n",
+        ")\n",
+        "\n",
+        "print(ОТВЕТ)\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}