初始化项目，由ModelHub XC社区提供模型

Model: Alelcv27/Llama3.1-8B-Base-ModelStock-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 +1,45 @@
+---
+base_model:
+- meta-llama/Llama-3.1-8B
+- Alelcv27/Llama3.1-8B-Base-Math
+- Alelcv27/Llama3.1-8B-Base-Code
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Llama3.1-8B-Base-ModelStock-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 [Model Stock](https://arxiv.org/abs/2403.19522) 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: bfloat16
+merge_method: model_stock
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Math
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Code
+      - layer_range: [0, 32]
+        model: meta-llama/Llama-3.1-8B
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "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 +1,13 @@
+base_model: meta-llama/Llama-3.1-8B
+dtype: bfloat16
+merge_method: model_stock
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Math
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Base-Code
+      - layer_range: [0, 32]
+        model: meta-llama/Llama-3.1-8B

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e731af3ea9a4c842635c3ca34280531df85f1c3a6de0746cf41538a1f951eb4
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f3f9e78c429fec6aa38895e11a0278128a321ba13091f673cb9393580a8374
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d1d37a5caf913013f7fd8c07242a30d9d48d3a7ec0017af3483f8b1c14d81a
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fe29b91086765fd2a5501d358828b2c58dde82e1637618212d4fae0b92273a
+size 1191234472

special_tokens_map.json

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