初始化项目，由ModelHub XC社区提供模型

Model: thelamapi/next-270m Source: Original Platform
2026-06-19 21:17:26 +08:00
commit 5b696cb2aa
15 changed files with 51871 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,44 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+next-270m-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+next-270m-f16.gguf filter=lfs diff=lfs merge=lfs -text
+next-270m-f32.gguf filter=lfs diff=lfs merge=lfs -text
+assets/bnr.png filter=lfs diff=lfs merge=lfs -text
+assets/banner.png filter=lfs diff=lfs merge=lfs -text
+assets/bannsr.png filter=lfs diff=lfs merge=lfs -text
+assets/banne5r.png filter=lfs diff=lfs merge=lfs -text
+assets/banner3basic.png filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,308 @@
+---
+language: tr
+license: mit
+tags:
+- turkish
+- türkiye
+- english
+- ai
+- lamapi
+- gemma3
+- next
+- next-x1
+- efficient
+- text-generation
+- open-source
+- 1b
+- 270m
+- finetune
+- gguf
+- huggingface
+- large-language-model
+- llm
+- causal
+- transformer
+- artificial-intelligence
+- machine-learning
+- ai-research
+- natural-language-processing
+- nlp
+- finetuned
+- lightweight
+- creative
+- summarization
+- question-answering
+- chat-model
+- generative-ai
+- optimized-model
+- unsloth
+- trl
+- sft
+- chemistry
+- biology
+- finance
+- legal
+- music
+- art
+- code
+- climate
+- medical
+- agent
+- text-generation-inference
+pipeline_tag: text-generation
+datasets:
+- mlabonne/FineTome-100k
+- ITCL/FineTomeOs
+- Gryphe/ChatGPT-4o-Writing-Prompts
+- dongguanting/ARPO-SFT-54K
+- GreenerPastures/All-Your-Base-Full
+- Gryphe/Opus-WritingPrompts
+- HuggingFaceH4/MATH-500
+- mlabonne/smoltalk-flat
+- mlabonne/natural_reasoning-formatted
+- OpenSPG/KAG-Thinker-training-dataset
+- uclanlp/Brief-Pro
+- CognitiveKernel/CognitiveKernel-Pro-SFT
+- SuperbEmphasis/Claude-4.0-DeepSeek-R1-RP-SFWish
+- QuixiAI/dolphin-r1
+- mlabonne/lmsys-arena-human-sft-55k
+library_name: transformers
+---
+
+<img src='assets/banner.png'>
+
+# 🚀 Next-270M (xt330)
+
+### *Lightweight, Efficient, and Türkiye-Focused AI*
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![Language: English](https://img.shields.io/badge/Language-Multilingual-red.svg)]()
+[![HuggingFace](https://img.shields.io/badge/🤗-Lamapi/Next--270M-orange.svg)](https://huggingface.co/Lamapi/next-270m)
+[![Discord](https://cdn.modrinth.com/data/cached_images/e84c69448cbf878a167f996d63e1a253437fcea2.png)](https://discord.gg/XgH4EpyPD2)
+
+---
+
+<style>
+  table { width:fit-content; border-collapse:separate; border-spacing:0 3px;font-family:system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;background:rgba(15,22,32,0.4);border-radius:16px;padding: 10px; border:none;transition:.2s all ease;}
+  thead th { text-align:center; padding:4px 10px; font-size:13px; text-transform:uppercase; color:rgb(200,200,200);border:none; }
+  tbody tr { transition: transform 0.18s ease, box-shadow 0.18s ease; border:none !important;transition:.2s all ease;border-radius:16px;background:rgba(0, 0, 0, 0.38);}
+  tbody .turkish:hover {box-shadow:0 6px 15px rgba(0, 0, 0, 0.27);scale:1.01;background:rgba(80, 38, 38, 0.6);}
+  tbody .next:hover {box-shadow:0 6px 15px rgba(0, 0, 0, 0.27);scale:1.02;background: rgba(0, 59, 225, 1)}
+  tbody tr:hover { box-shadow:0 0px 15px rgba(102, 102, 102, 0.13); background:rgba(139, 139, 139, 0.16)}
+  td { padding:8px 10px;border:0px transparent !important;outline:transparent !important; text-align:center; }
+  td:first-child { font-weight:600;text-align:left }
+  /* tbody .turkish td { background: rgba(255, 0, 0, 0.2) !important; color:rgb(200,200,200); font-weight:400;border:0px !important; scale:1.0; } */
+  /* tbody .next td { background: rgba(0, 89, 255, 0.49)!important; color:rgb(200,200,200); font-weight:600;border:0px !important; scale:1.00;outline:none;border:none !important;} */
+  .next{
+    background: rgba(0, 89, 255, 0.49);
+  }
+  .turkish{
+    background:rgba(51, 34, 34, 0.64);
+  }
+  tbody tr td:first-child { border-top-left-radius:12px; border-bottom-left-radius:12px; }
+  tbody tr td:last-child { border-top-right-radius:12px; border-bottom-right-radius:12px; } strong{
+    font-size:16px;font-weight:700;
+  }
+  em{opacity:0.7;font-size:11px !important;}
+</style>
+## 📖 Overview
+
+**Next-270M** is a **270-million parameter causal language model** based on **Gemma 3**, designed for **efficiency, low-resource deployment, and reasoning-focused natural language understanding**.
+
+Key highlights:
+
+* Extremely **lightweight** — can run on consumer GPUs with low VRAM.
+* Optimized for **text reasoning, summarization, and creative generation**.
+* Supports **Turkish natively** while remaining multilingual.
+* Open-source and transparent for research and applications.
+
+Ideal for **developers, students, and organizations** needing **fast, reliable, and low-resource text-generation**.
+
+---
+
+# Our Next 1B and Next 4B models are leading to all of the tiny models in benchmarks. 
+
+<table>
+  <thead>
+    <tr>
+      <th>Model</th>
+      <th>MMLU (5-shot) %</th>
+      <th>MMLU-Pro %</th>
+      <th>GSM8K %</th>
+      <th>MATH %</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr class="next">
+      <td data-label="Model">Next 4B preview <em>Version s325</em></td>
+      <td data-label="MMLU (5-shot) %">84.6</td>
+      <td data-label="MMLU-Pro %">66.9</td>
+      <td data-label="GSM8K %">82.7</td>
+      <td data-label="MATH %"><strong>70.5</strong></td>
+    </tr>
+    <tr class="next">
+      <td data-label="Model">Next 1B <em>Version t327</em></td>
+      <td data-label="MMLU (5-shot) %"><strong>87.3</strong></td>
+      <td data-label="MMLU-Pro %"><strong>69.2</strong></td>
+      <td data-label="GSM8K %"><strong>90.5</strong></td>
+      <td data-label="MATH %">70.1</td>
+    </tr>
+    <tr>
+      <td data-label="Model">Qwen 3 0.6B</td>
+      <td data-label="MMLU (5-shot) %">52.81</td>
+      <td data-label="MMLU-Pro %">37.6</td>
+      <td data-label="GSM8K %">60.7</td>
+      <td data-label="MATH %">20.5</td>
+    </tr>
+    <tr>
+      <td data-label="Model">Llama 3.2 1B</td>
+      <td data-label="MMLU (5-shot) %">49.3</td>
+      <td data-label="MMLU-Pro %">44.4</td>
+      <td data-label="GSM8K %">11.9</td>
+      <td data-label="MATH %">30.6</td>
+    </tr>
+    <tr class="turkish">
+      <td data-label="Model">Kumru 7B <em>not verified</em></td>
+      <td data-label="MMLU (5-shot) %">30.7</td>
+      <td data-label="MMLU-Pro %">28.6</td>
+      <td data-label="GSM8K %">15.38</td>
+      <td data-label="MATH %">6.4</td>
+    </tr>
+  </tbody>
+</table>
+
+---
+
+# Also, our Next Z1 model is leading to state-of-the-art models in some of the Benchmarks.
+<table>
+  <thead>
+    <tr>
+      <th>Model</th>
+      <th>MMLU (5-shot) %</th>
+      <th>MMLU-Pro %</th>
+      <th>GSM8K %</th>
+      <th>MATH %</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr class="next">
+      <td data-label="Model">Next Z1 <em>Version l294</em></td>
+      <td data-label="MMLU (5-shot) %"><strong>97.3</strong></td>
+      <td data-label="MMLU-Pro %"><strong>94.2</strong></td>
+      <td data-label="GSM8K %">97.7</td>
+      <td data-label="MATH %">93.2</td>
+    </tr>
+    <tr class="next">
+      <td data-label="Model">Next Z1 <em>Version l294</em> (no tool)</td>
+      <td data-label="MMLU (5-shot) %">94.7</td>
+      <td data-label="MMLU-Pro %">90.1</td>
+      <td data-label="GSM8K %">94.5</td>
+      <td data-label="MATH %">88.7</td>
+    </tr>
+    <tr>
+      <td data-label="Model">GPT 5</td>
+      <td data-label="MMLU (5-shot) %">92.5</td>
+      <td data-label="MMLU-Pro %">87.0</td>
+      <td data-label="GSM8K %"><strong>98.4</strong></td>
+      <td data-label="MATH %"><strong>96.0</strong></td>
+    </tr>
+    <tr>
+      <td data-label="Model">Claude Opus 4.1 (Thinking)</td>
+      <td data-label="MMLU (5-shot) %">~92.0</td>
+      <td data-label="MMLU-Pro %">87.8</td>
+      <td data-label="GSM8K %">84.7</td>
+      <td data-label="MATH %">95.4</td>
+    </tr>
+  </tbody>
+</table>
+
+---
+
+## 🎯 Goals
+
+1. **Lightweight Efficiency:** Run smoothly on low-resource devices.
+2. **Reasoning-Focused:** Provide logical and coherent text outputs.
+3. **Accessibility:** Fully open-source with clear documentation.
+4. **Multilingual Adaptability:** Turkish-focused but supports other languages.
+
+---
+
+## ✨ Key Features
+
+| Feature                     | Description                                                           |
+| --------------------------- | --------------------------------------------------------------------- |
+| 🔋 Lightweight Architecture | Optimized for low VRAM usage; ideal for small GPUs or CPU deployment. |
+| 🇹🇷 Turkish & Multilingual | Handles complex Turkish prompts accurately.                           |
+| 🧠 Reasoning Capabilities   | Logical chain-of-thought for question-answering and problem-solving.  |
+| 📊 Consistent Outputs       | Reliable and reproducible results across multiple runs.               |
+| 🌍 Open Source              | Transparent, research-friendly, and community-driven.                 |
+
+---
+
+## 📐 Model Specifications
+
+| Specification      | Details                                                                |
+| ------------------ | ---------------------------------------------------------------------- |
+| Base Model         | Gemma 3                                                           |
+| Parameter Count    | 270 Million                                                              |
+| Architecture       | Transformer, causal LLM                                                |
+| Fine-Tuning Method | Instruction fine-tuning (SFT) with Turkish and multilingual datasets   |
+| Optimizations      | Quantization-ready (q8, f16, f32)                      |
+| Use Cases          | Text generation, summarization, Q&A, creative writing, reasoning tasks |
+
+---
+
+## 🚀 Installation & Usage
+
+### Use the model:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "Lamapi/next-270m"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+# Chat message
+messages = [
+    {"role": "system", "content": "You are Next-X1, a smart and concise AI assistant trained by Lamapi. Always respond in the user's language. Proudly made in Turkey."},
+    {"role": "user", "content": "Hello, how are you?"}
+]
+
+# Prepare input with Tokenizer
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(prompt, return_tensors="pt")
+
+# Output from the model
+output = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+<div style='width:700px;'>
+  <div style='background-color:rgba(0,140,255,0.5);border-radius:16px;border-bottom-right-radius:0px;padding:3px 10px;width:fit-content;max-width:400px;margin-left:250px;margin-top:-15px;margin-bottom:10px;'>
+    Hello, how are you?
+  </div>
+  <div style='background-color:rgba(42,42,40,0.7);border-radius:16px;border-bottom-left-radius:0px;padding:3px 10px;width:fit-content;max-width:400px;'>
+  I'm fine, thank you. How are you?
+  </div>
+</div>
+
+---
+
+## 📄 License
+
+MIT License — free to use, modify, and distribute. Attribution appreciated.
+
+---
+
+## 📞 Contact & Support
+
+* 📧 **Email:** [lamapicontact@gmail.com](mailto:lamapicontact@gmail.com)
+* 🤗 **HuggingFace:** [Lamapi](https://huggingface.co/Lamapi)
+
+---
+
+> **Next-270M** — Lightweight, **efficient, and reasoning-focused**, bringing **Turkey’s AI forward** on low-resource hardware.
+
+[![Follow on HuggingFace](https://img.shields.io/badge/Follow-HuggingFace-yellow?logo=huggingface)](https://huggingface.co/Lamapi)
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}
--- a/assets/banner.png
+++ b/assets/banner.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22dc2644a59ed9760ed2dcbb255aaa780edaf6c88cc226381831153e6cd90f7c
+size 114527
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,56 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "eos_token_id": 106,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.10.5",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.4"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6903c5db993aead89b677a594d2519345e59f6e4040b0c5e423d1a79cd95ebb
+size 536223056
--- a/next-270m-f16.gguf
+++ b/next-270m-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa39dadf495322779213cfce7bc00e9f7a0cff4e8228050312be61c310a5ab4
+size 542834880
--- a/next-270m-f32.gguf
+++ b/next-270m-f32.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064f554bab049f2134d5507ab2704471ae908906b826ff7e7dc75a127e25c56e
+size 1078919360
--- a/next-270m-q8_0.gguf
+++ b/next-270m-q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152e268e21a6993b6a84c28d46bfc2a6a027ee8042ca070773869f4860380729
+size 291545280
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074
--- a/tokenizer_config.json
+++ b/tokenizer_config.json