初始化项目，由ModelHub XC社区提供模型

Model: eren23/Experiment26-12B
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 +1,89 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+base_model:
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+- yam-peleg/Experiment26-7B
+license: cc-by-nc-4.0
+language:
+- en
+---
+
+# Experiment26-12B
+
+Experiment26-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+
+## 🧩 Configuration
+
+```yaml
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [4, 12]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [8, 16]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [12, 20]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [16, 24]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [20, 28]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [24, 32]
+    model: yam-peleg/Experiment26-7B
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "eren23/Experiment26-12B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "yam-peleg/Experiment26-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,25 @@
+
+dtype: float16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [4, 12]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [8, 16]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [12, 20]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [16, 24]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [20, 28]
+    model: yam-peleg/Experiment26-7B
+- sources:
+  - layer_range: [24, 32]
+    model: yam-peleg/Experiment26-7B

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b72f304eaa6a5aec64daf077978f26ae8ab54099a21c6df6840913f07c4db64
+size 9909394184

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40addfdbe999c4a33682ce952a8ccc14c76986b80bbde34f922e2aba11e07312
+size 9976577160

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c968a6e35f4032d34db27eb8d1863b5140e1701a15755c2a9e57f5d2569e1a55
+size 5066927400

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}