初始化项目，由ModelHub XC社区提供模型

Model: puettmann/LlaMaestra-3.2-1B-Translation
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 +1,67 @@
+---
+library_name: transformers
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+license: llama3.2
+language:
+- en
+- it
+tags:
+- translation
+- text-generation
+---
+# LlaMaestra - A tiny Llama model tuned for text translation
+```html
+ _     _      ___  ___                _             
+| |   | |     |  \/  |               | |            
+| |   | | __ _| .  . | __ _  ___  ___| |_ _ __ __ _ 
+| |   | |/ _` | |\/| |/ _` |/ _ \/ __| __| '__/ _` |
+| |___| | (_| | |  | | (_| |  __/\__ \ |_| | | (_| |
+\_____/_|\__,_\_|  |_/\__,_|\___||___/\__|_|  \__,_|
+```
+
+> For EN-IT translation, check out the [lightweight Quadrifoglio models](https://huggingface.co/collections/LeonardPuettmann/quadrifoglio-6769eb87036c3cd7f38cc921) as well.
+
+## Model Card 
+This model was finetuned with roughly 300.000 examples of translations from English to Italian and Italian to English. The model was finetuned in a way to more directly provide a translation without much explanation.
+
+Finetuning took about 10 hours on an A10G Nvidia GPU.
+
+Due to its size, the model runs very well on CPUs. 
+![A very italian Llama model](llamaestro-sm-bg.png)
+
+## Usage 
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "LeonardPuettmann/LlaMaestra-3.2-1B-Instruct-v0.1"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, add_bos_token=True, trust_remote_code=True)
+
+row_json = [
+    {"role": "system", "content": "Your job is to return translations for sentences or words from either Italian to English or English to Italian."},
+    {"role": "user", "content": "Do you sell tickets for the bus?"},
+]
+
+prompt =  tokenizer.apply_chat_template(row_json, tokenize=False)
+model_input = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+with torch.no_grad():
+    print(tokenizer.decode(model.generate(**model_input, max_new_tokens=1024)[0]))
+```
+
+## Data used 
+The source for the data were sentence pairs from tatoeba.com. The data can be downloaded from here: https://tatoeba.org/downloads
+
+## Credits
+
+Base model: `meta-llama/Llama-3.2-1B-Instruct`
+Finetuned by: Leonard Püttmann https://www.linkedin.com/in/leonard-p%C3%BCttmann-4648231a9/

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "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": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c9895c0dcbd4eeb227c4dadc63ec8a006e533a00e3fda5eed2ee092ba3ab81
+size 2471645464

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920