Views
No views yet
1models:
2- model: automerger/OgnoExperiment27-7B
3 # No parameters necessary for base model
4- model: ammarali32/multi_verse_model
5 parameters:
6 density: 0.53
7 weight: 0.6
8merge_method: dare_ties
9base_model: automerger/OgnoExperiment27-7B
10parameters:
11int8_mask: true
12dtype: bfloat16
13random_seed: 0
14 ```
15
16## 💻 Usage
17
18```python
19!pip install -qU transformers accelerate
20
21from transformers import AutoTokenizer
22import transformers
23import torch
24
25model = "automerger/Ognoexperiment27Multi_verse_model-7B"
26messages = [{"role": "user", "content": "What is a large language model?"}]
27
28tokenizer = AutoTokenizer.from_pretrained(model)
29prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
30pipeline = transformers.pipeline(
31 "text-generation",
32 model=model,
33 torch_dtype=torch.float16,
34 device_map="auto",
35)
36
37outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
38print(outputs[0]["generated_text"])