Update README.md

README.md

@@ -1,56 +1,47 @@
 ---
 base_model:
-- NousResearch/Hermes-2-Theta-Llama-3-8B
-- camillop/Meta-Llama-3-8B-ORPO-ITA-llama-adapters
-- gradientai/Llama-3-8B-Instruct-Gradient-1048k
-- openchat/openchat-3.6-8b-20240522
-- hfl/llama-3-chinese-8b-instruct-v2-lora
-- Vdr1/L3-8B-sunfall-Stheno-v3.1
-- hfl/llama-3-chinese-8b-instruct-v2-lora
-- migtissera/Llama-3-8B-Synthia-v3.5
-- unstoppable123/LLaMA3-8B_chinese_lora_sft_v0.2
-- shenzhi-wang/Llama3-8B-Chinese-Chat
-- Jiar/Llama-3-8B-Chinese
-- Sao10K/L3-8B-Stheno-v3.2
-- shibing624/llama-3-8b-instruct-262k-chinese-lora
+- wwe180/L3-8B-LingYang-v1
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+- Llama3
+license:
+- other
 ---
+
+#The model is experimental, so the results cannot be guaranteed.
+
 # merge
 
 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 [gradientai/Llama-3-8B-Instruct-Gradient-1048k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-1048k) as a base.
+## 💻 Usage
 
-### Models Merged
+```python
+!pip install -qU transformers accelerate
 
-The following models were included in the merge:
-* [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) + [camillop/Meta-Llama-3-8B-ORPO-ITA-llama-adapters](https://huggingface.co/camillop/Meta-Llama-3-8B-ORPO-ITA-llama-adapters)
-* [openchat/openchat-3.6-8b-20240522](https://huggingface.co/openchat/openchat-3.6-8b-20240522) + [hfl/llama-3-chinese-8b-instruct-v2-lora](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2-lora)
-* [Vdr1/L3-8B-sunfall-Stheno-v3.1](https://huggingface.co/Vdr1/L3-8B-sunfall-Stheno-v3.1) + [hfl/llama-3-chinese-8b-instruct-v2-lora](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2-lora)
-* [migtissera/Llama-3-8B-Synthia-v3.5](https://huggingface.co/migtissera/Llama-3-8B-Synthia-v3.5) + [unstoppable123/LLaMA3-8B_chinese_lora_sft_v0.2](https://huggingface.co/unstoppable123/LLaMA3-8B_chinese_lora_sft_v0.2)
-* [shenzhi-wang/Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) + [Jiar/Llama-3-8B-Chinese](https://huggingface.co/Jiar/Llama-3-8B-Chinese)
-* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) + [shibing624/llama-3-8b-instruct-262k-chinese-lora](https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese-lora)
+from transformers import AutoTokenizer
+import transformers
+import torch
 
-### Configuration
+model = "L3-8B-LingYang-v1"
+messages = [{"role": "user", "content": "What is a large language model?"}]
 
-The following YAML configuration was used to produce this model:
-
-```yaml
-models:
-  - model: shenzhi-wang/Llama3-8B-Chinese-Chat+Jiar/Llama-3-8B-Chinese
-  - model: NousResearch/Hermes-2-Theta-Llama-3-8B+camillop/Meta-Llama-3-8B-ORPO-ITA-llama-adapters
-  - model: migtissera/Llama-3-8B-Synthia-v3.5+unstoppable123/LLaMA3-8B_chinese_lora_sft_v0.2
-  - model: openchat/openchat-3.6-8b-20240522+hfl/llama-3-chinese-8b-instruct-v2-lora
-  - model: Sao10K/L3-8B-Stheno-v3.2+shibing624/llama-3-8b-instruct-262k-chinese-lora
-  - model: Vdr1/L3-8B-sunfall-Stheno-v3.1+hfl/llama-3-chinese-8b-instruct-v2-lora
-merge_method: model_stock
-base_model: gradientai/Llama-3-8B-Instruct-Gradient-1048k
-dtype: bfloat16
+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",
+)
 ```
+## Statement:
+
+L3-8B-LingYang-v1 does not represent the views and positions of the model developers We will not be liable for any problems arising from the use of the L3-8B-LingYang-v1 open Source model, including but not limited to data security issues, risk of public opinion, or any risks and problems arising from the misdirection, misuse, dissemination or misuse of the model.
+
+
+
+