初始化项目，由ModelHub XC社区提供模型

Model: ruggsea/dante-zero-2025-03-05
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 +1,69 @@
+---
+license: apache-2.0
+language:
+- it
+base_model:
+- PleIAs/Pleias-350m-Preview
+pipeline_tag: text-generation
+tags:
+- poetry
+library_name: transformers
+---
+# Dante-Zero Fine-tuned Model
+
+This model was fine-tuned using Reinforcement Learning with Group Relative Policy Optimization (GRPO) to generate Dante-style poetry in endecasillabi (11-syllable lines).
+
+## Model Details
+
+- **Base Model:** PleIAs/Pleias-350m-Preview
+- **Training Method:** GRPO (Group Relative Policy Optimization )
+- **Training Data:** 1,000 chunks from Dante's Divine Comedy
+- **Epochs:** 10
+- **Trained By:** ruggsea
+- **Date:** 2025-03-05
+
+## Model Description
+
+This model is specialized in generating Italian poetry in the style of Dante Alighieri's Divine Comedy. It has been trained to:
+
+1. Generate proper endecasillabi (11-syllable lines)
+2. Follow the structure of Dante's poetry
+3. Avoid repetition
+4. Create original content (not plagiarize the Divine Comedy)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("ruggsea/dante-zero-2025-03-05")
+tokenizer = AutoTokenizer.from_pretrained("ruggsea/dante-zero-2025-03-05")
+
+# Generate poetry
+prompt = "Nel mezzo del cammin di nostra vita"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(
+    inputs.input_ids,
+    max_new_tokens=200,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    repetition_penalty=1.2
+)
+generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(generated_text)
+```
+
+## Reward Functions
+
+The model was trained using several reward functions:
+
+1. **Endecasillabo Checker:** Rewards proper 11-syllable lines
+2. **Plagiarism Checker:** Penalizes copying from the Divine Comedy
+3. **Verse Structure Checker:** Encourages verse-like structure
+4. **Repetition Penalty:** Discourages repetitive patterns
+
+## License
+
+This model is available under the same license as the base model (PleIAs/Pleias-350m-Preview).

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "PleIAs/Pleias-350m-Preview",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c353e29cdfc442a642ead972a2407b467a7f93694d614db2bf9a908f6d1c603e
+size 706875632

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|end_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": "<|end_of_text|>",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]",
+  "use_token_type_ids": false,
+  "vocab_size": 65536
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e715216741604a6e077ba2b09630723e606676f5b8960f15b645bdf2bca79b1
+size 5752