初始化项目，由ModelHub XC社区提供模型

Model: rasyosef/Llama-3.2-1B-Amharic
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,59 @@
+---
+widget:
+- text: አዲስ አበባ
+  example_title: Example 1
+- text: በኢንግሊዝ ፕሪምየር ሊግ
+  example_title: Example 2
+- text: ዶናልድ ትራምፕ
+  example_title: Example 3
+language:
+- am
+metrics:
+- perplexity
+library_name: transformers
+pipeline_tag: text-generation
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+---
+
+# Llama-3.2-Amharic-1B
+
+This model is a version of Meta's [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) decoder transformer model that was continuously pretrained on an Amharic text corpus. 
+
+- 16k new amharic tokens were added to the Llama 3.2 tokenizer and the embdedding layer of the model was resized accordingly. 
+- The model was then trained on **300 million tokens** of **Amharic** text.
+- This is a base model. The Amharic instruction following version is [Llama-3.2-1B-Amharic-Instruct](https://huggingface.co/rasyosef/Llama-3.2-1B-Amharic-Instruct)
+
+### How to use
+First, you need to install the latest version of transformers
+```
+pip install -Uq transformers
+```
+
+You can use this model directly with a pipeline for text generation:
+
+```python
+from transformers import pipeline
+
+llama_am = pipeline(
+    "text-generation",
+    model="rasyosef/Llama-3.2-1B-Amharic",
+    device_map="auto"
+  )
+
+prompt = "በኢንግሊዝ ፕሪምየር ሊግ"
+llama_am(
+    prompt,
+    max_new_tokens=128,
+    temperature=0.3,
+    do_sample=True,
+    top_k=8,
+    top_p=0.8,
+    repetition_penalty=1.05
+  )
+```
+
+Output:
+```python
+[{'generated_text': 'በኢንግሊዝ ፕሪምየር ሊግ የ2017/18 የውድድር ዘመን ላይ ተሳታፊ የሆነው ሊቨርፑል ትናንት ምሽት 3 :45 ላይ ከዌስትሀም ዩናይትድ ጋር ባደረገው ጨዋታ በ2 ለ 1 ውጤት ተሸንፏል ።'}]
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "yosefw/llama-3.2-1b-amharic-16k-v3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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,
+  "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": "float16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 143424
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e4c3377526b918ef9f25a1a230325280ba69e6007d4022f5cb63a14304071f
+size 2533773600

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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712d0424187d5a4d2304e5d57bdc237178de06f0f83536b367ecacbbc292802e
+size 19215081