初始化项目，由ModelHub XC社区提供模型

Model: Etherll/Tashkeel-700M
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,87 @@
+---
+base_model: LiquidAI/LFM2-700M
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- lfm2
+- trl
+- sft
+- arabic
+license: apache-2.0
+language:
+- ar
+datasets:
+- arbml/tashkeela
+---
+
+# Tashkeel-700M
+
+**Arabic Diacritization Model** | **نَمُوذِجٌ تَشْكِيلُ النُّصُوصِ الْعَرَبِيَّةِ**
+
+نموذج بحجم 700 مليون بارامتر مخصص لتشكيل النصوص العربية. تم تدريب هذا النموذج بضبط نموذج 
+
+`LiquidAI/LFM2-700M` 
+
+على مجموعة البيانات
+
+ `arbml/tashkeela`.
+
+- **النموذج الأساسي:** [LiquidAI/LFM2-700M](https://huggingface.co/LiquidAI/LFM2-700M)
+- **مجموعة البيانات:** [arbml/tashkeela](https://huggingface.co/datasets/arbml/tashkeela)
+
+### كيفية الاستخدام
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+#تحميل النموذج
+model_id = "Etherll/Tashkeel-700M"
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype="bfloat16",
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# إضافة التشكيل
+prompt = "السلام عليكم" 
+input_ids = tokenizer.apply_chat_template(
+    [{"role": "user", "content": prompt}],
+    add_generation_prompt=True,
+    return_tensors="pt",
+    tokenize=True,
+).to(model.device)
+
+output = model.generate(
+    input_ids,
+    do_sample=False,  
+)
+
+print(tokenizer.decode(output[0, input_ids.shape[-1]:], skip_special_tokens=True))
+```
+
+### مثال
+*   **النص المدخل:** `السلام عليكم`
+*   **الناتج:** `السَّلَامُ عَلَيْكُمْ`
+
+---
+---
+
+# Tashkeel-700M (English)
+
+A 700M parameter model for Arabic diacritization (Tashkeel). This model is a fine-tune of `LiquidAI/LFM2-700M` on the `arbml/tashkeela` dataset.
+
+- **Base Model:** [LiquidAI/LFM2-700M](https://huggingface.co/LiquidAI/LFM2-700M)
+- **Dataset:** [arbml/tashkeela](https://huggingface.co/datasets/arbml/tashkeela)
+
+### How to Use
+The Python code for usage is the same as listed in the Arabic section above.
+
+### Example
+*   **Input:** `السلام عليكم`
+*   **Output:** `السَّلَامُ عَلَيْكُمْ`
+
+This lfm2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

chat_template.jinja

@@ -0,0 +1,37 @@
+{{- bos_token -}}
+{%- set system_prompt = "" -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+	{%- set ns.system_prompt = messages[0]["content"] -%}
+	{%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+	{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
+	{%- for tool in tools -%}
+		{%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+		{%- endif -%}
+		{%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+	{%- endfor -%}
+	{%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+	{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+	{{- "<|im_start|>" + message["role"] + "\n" -}}
+	{%- set content = message["content"] -%}
+	{%- if content is not string -%}
+		{%- set content = content | tojson -%}
+	{%- endif -%}
+	{%- if message["role"] == "tool" -%}
+		{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
+	{%- endif -%}
+	{{- content + "<|im_end|>\n" -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+	{{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1536,
+  "block_ff_dim": 10240,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1536,
+  "conv_dim_out": 1536,
+  "conv_use_xavier_init": true,
+  "eos_token_id": 7,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 24,
+  "num_heads": 24,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 1000000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "unsloth_version": "2025.8.9",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "max_length": 128000,
+  "pad_token_id": 0,
+  "transformers_version": "4.55.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6086b80ccbd7d047d08ae3ef75eb4b47bfbb2d958432fe90f1ccac896a266385
+size 1484995328

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}