eren23 commited on
Commit
7634cb6
1 Parent(s): 3423625

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - mlabonne/NeuralBeagle14-7B
7
+ - mlabonne/DareBeagle-7B-v2
8
+ base_model:
9
+ - mlabonne/NeuralBeagle14-7B
10
+ - mlabonne/DareBeagle-7B-v2
11
+ ---
12
+
13
+ # NeuralDareBeagle-7B-slerp
14
+
15
+ NeuralDareBeagle-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
17
+ * [mlabonne/DareBeagle-7B-v2](https://huggingface.co/mlabonne/DareBeagle-7B-v2)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: mlabonne/NeuralBeagle14-7B
25
+ layer_range: [0, 32]
26
+ - model: mlabonne/DareBeagle-7B-v2
27
+ layer_range: [0, 32]
28
+ merge_method: slerp
29
+ base_model: OpenPipe/mistral-ft-optimized-1218
30
+ parameters:
31
+ t:
32
+ - filter: self_attn
33
+ value: [0.9, 0.7, 0.8, 0.7, 0.98]
34
+ - filter: mlp
35
+ value: [0.1, 0.3, 0.2, 0.3, 0.02]
36
+ - value: 0.45
37
+ dtype: bfloat16
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "eren23/NeuralDareBeagle-7B-slerp"
50
+ messages = [{"role": "user", "content": "What is a large language model?"}]
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained(model)
53
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
+ pipeline = transformers.pipeline(
55
+ "text-generation",
56
+ model=model,
57
+ torch_dtype=torch.float16,
58
+ device_map="auto",
59
+ )
60
+
61
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
+ print(outputs[0]["generated_text"])
63
+ ```