初始化项目，由ModelHub XC社区提供模型

Model: anakin87/Llama-3-8b-ita-ties-pro
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 +1,64 @@
+---
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+- DeepMount00/Llama-3-8b-Ita
+- swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: llama3
+language:
+- it
+---
+# Llama-3-8b-ita-ties-pro
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+I tried to merge two of the best Italian LLMs using Mergekit. The results are acceptable, but I could not improve on the best existing model.
+
+## Evaluation
+
+For a detailed comparison of model performance, check out the [Leaderboard for Italian Language Models](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard).
+
+Here's a breakdown of the performance metrics:
+
+| Metric                      | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
+|:----------------------------|:----------------------|:----------------|:---------------------|:--------|
+| **Accuracy Normalized**     | 0.6967                | 0.5646        | 0.5717              | 0.6110  |
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita)
+* [swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA](https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+models:
+  - model: meta-llama/Meta-Llama-3-8B-Instruct
+    # no parameters necessary for base model
+  - model: swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
+    parameters:
+      density: 0.7
+      weight: 0.6
+  - model: DeepMount00/Llama-3-8b-Ita
+    parameters:
+      density: 0.7
+      weight: 0.3
+merge_method: ties
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+parameters:
+  normalize: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "eos_token_id": [128001, 128009],
+  "do_sample": true,
+  "temperature": 0.6,
+  "max_length": 4096,
+  "top_p": 0.9,
+  "transformers_version": "4.40.1"
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+models:
+  - model: meta-llama/Meta-Llama-3-8B-Instruct
+    # no parameters necessary for base model
+  - model: swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
+    parameters:
+      density: 0.7
+      weight: 0.6
+  - model: DeepMount00/Llama-3-8b-Ita
+    parameters:
+      density: 0.7
+      weight: 0.3
+merge_method: ties
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+parameters:
+  normalize: true
+dtype: bfloat16

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8095e5ed0b6ac33c952a84a60c92b32a30e94bf71fcfbc7e606d17e04264aa94
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fb071850a21b94e7107a3ee11f3ad5722a47fb1f2801759db141a60934a3f5
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352310597ffb4cab7a1c0e1f68127ab909fea973e8110f20b297cd87ec74fb54
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7245fabcdf64aa924f87d8659fa153559c357f8b054bc97f4c7e2d7341555a8f
+size 1191234472

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
+  }
+}