初始化项目，由ModelHub XC社区提供模型

Model: Sheikhaei/llama-3.2-1b-english-persian-translator
Source: Original Platform

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+language:
+  - en
+  - fa
+tags:
+  - translation
+  - english-to-persian
+  - persian-to-english
+  - bilingual
+model_type: llama
+base_model: meta-llama/Llama-3.2-1B
+widget:
+  - text: |
+      ### English:
+      The children were playing in the park.
+      ### Persian:
+  - text: |
+      ### Persian:
+      من به مدرسه می‌روم.
+      ### English:    
+---
+
+
+# LLaMA 3.2 1B – English ↔ Persian Translator
+
+This model is a fine-tuned version of [`meta-llama/Llama-3.2-1B`](https://huggingface.co/meta-llama/Llama-3.2-1B), trained for **bidirectional translation** between **English and Persian**. It supports both:
+
+- 🇬🇧 English → 🇮🇷 Persian
+- 🇮🇷 Persian → 🇬🇧 English
+
+---
+
+## Format
+
+The model expects prompts in the following format:
+
+```
+### English:
+The children were playing in the park.
+### Persian:
+```
+or
+
+```
+### Persian:
+کودکان در پارک بازی می‌کردند.
+### English:
+```
+---
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("Sheikhaei/llama-3.2-1b-en-fa-translator")
+tokenizer = AutoTokenizer.from_pretrained("Sheikhaei/llama-3.2-1b-en-fa-translator")
+
+prompt = """### English:
+The children were playing in the park.
+### Persian:
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100, do_sample=False)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Training Data
+
+This model was fine-tuned on a custom English–Persian parallel dataset containing ~640,000 sentence pairs. The source data was collected from Tatoeba and then translated and expanded using the Gemma-3-12B model.
+
+## Evaluation
+
+| Direction     | BLEU | COMET |
+|---------------|------|------|
+| English → Persian | 0.47 | 0.89 |
+| Persian → English | 0.58 | 0.91 |
+
+## License
+
+Apache 2.0
+

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+language:
+  - en
+  - fa
+tags:
+  - translation
+  - english-to-persian
+  - persian-to-english
+  - bilingual
+  - farsi
+  - persian
+model_type: llama
+base_model: meta-llama/Llama-3.2-1B
+pipeline_tag: text-generation
+library: transformers
+widget:
+  - text: |
+      ### English:
+      The children were playing in the park.
+      ### Persian:
+  - text: |
+      ### Persian:
+      من به مدرسه می‌روم.
+      ### English:    
+---
+
+[![Space](https://img.shields.io/badge/🤗%20Spaces-Try%20it%20here-blue)](https://huggingface.co/spaces/Sheikhaei/llama-3.2-1b-english-persian-translator)
+
+
+# LLaMA 3.2 1B – English ↔ Persian Translator
+
+This model is a fine-tuned version of [`meta-llama/Llama-3.2-1B`](https://huggingface.co/meta-llama/Llama-3.2-1B), trained for **bidirectional translation** between **English and Persian**. It supports both:
+
+- 🇬🇧 English → 🇮🇷 Persian
+- 🇮🇷 Persian → 🇬🇧 English
+
+---
+
+## Format
+
+The model expects prompts in the following format:
+
+```
+### English:
+The children were playing in the park.
+### Persian:
+```
+or
+
+```
+### Persian:
+کودکان در پارک بازی می‌کردند.
+### English:
+```
+---
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("Sheikhaei/llama-3.2-1b-en-fa-translator", torch_dtype="auto", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("Sheikhaei/llama-3.2-1b-en-fa-translator")
+
+prompt = """### English:
+The children were playing in the park.
+### Persian:
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=100, do_sample=False)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Training Data
+
+This model was fine-tuned on a custom English–Persian parallel dataset containing ~640,000 sentence pairs. The source data was collected from Tatoeba and then translated and expanded using the Gemma-3-12B model.
+
+## Evaluation
+
+| Direction     | BLEU | COMET |
+|---------------|------|------|
+| English → Persian | 0.47 | 0.89 |
+| Persian → English | 0.58 | 0.91 |
+
+## License
+
+Apache 2.0
+

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "vocab_size": 128257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.53.2"
+}

gguf/llama-3.2-1b-english-persian-translator-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d0f38183149cf07a83120e83c3b73a90f979646fdafe6b1388a5f0da2fb894
+size 1321081440

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53548b09e7804ca2b37f24cf0d975064ada5f0f14d81ba96794e05be2ae9e052
+size 2471649704

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
+size 17210102