初始化项目，由ModelHub XC社区提供模型

Model: Alelcv27/Llama3.1-8B-Base-DARETIES-Math-Code
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 +1,53 @@
+---
+base_model:
+- Alelcv27/Llama3.1-8B-Base-Math
+- meta-llama/Llama-3.1-8B
+- Alelcv27/Llama3.1-8B-Base-Code
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Llama3.1-8B-Base-DARETIES-Math-Code
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Alelcv27/Llama3.1-8B-Base-Math](https://huggingface.co/Alelcv27/Llama3.1-8B-Base-Math)
+* [Alelcv27/Llama3.1-8B-Base-Code](https://huggingface.co/Alelcv27/Llama3.1-8B-Base-Code)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: meta-llama/Llama-3.1-8B
+dtype: float16
+merge_method: dare_ties
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Math
+        parameters:
+          density: 0.8
+          weight: 0.6
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Code
+        parameters:
+          density: 0.6
+          weight: 0.5
+      - layer_range: [0, 32]
+        model: meta-llama/Llama-3.1-8B
+parameters:
+  normalize: 1.0
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "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": {
+    "factor": 8.0,
+    "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": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+base_model: meta-llama/Llama-3.1-8B
+dtype: float16
+merge_method: dare_ties
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Math
+        parameters:
+          density: 0.8
+          weight: 0.6
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Code
+        parameters:
+          density: 0.6
+          weight: 0.5
+      - layer_range: [0, 32]
+        model: meta-llama/Llama-3.1-8B
+parameters:
+  normalize: 1.0

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5363b3879b6626cdd5d4b9051971b41ee8d3bc67ff60f27c5692ecc12f8fba73
+size 4953586328

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f709283e9ec43f06aca9447d47ab566f0d173968a0c8bd5ababc02ee49e3955
+size 4999819232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b13651a2016a742654e99f4cf5f23301e4f34bc7efeada0929bc1ba4289f65a
+size 4915916048

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8714ad0261d5c8059ff598c656ab39db365ee6f640f1ffd15575ceeb2e12a56b
+size 1191234448

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>"
+}