Downloads · 30 days
6
11% of all-time downloads
Ksgk-fy/M7Percival_010.14-0.33-0.6-0.72-0.02-0.65-7B
M7Percival_010.14-0.33-0.6-0.72-0.02-0.65-7B is a text generation model from Ksgk-fy. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
6
11% of all-time downloads
All-time downloads
54
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
slices:
- sources:
- model: liminerity/M7-7b
layer_range: [0, 32]
- model: AurelPx/Percival_01-7b-slerp
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/M7-7b
parameters:
t:
- filter: self_attn
value: [0.13999352765818185, 0.32661882949922894, 0.59847467568124, 0.7195489079012326, 0.019959375479562835]
- filter: mlp
value: [0.8600064723418182, 0.6733811705007711, 0.2804510920987674, 0.2804510920987674, 0.9800406245204372]
- value: 0.6509267897374714
dtype: bfloat16
random_seed: 0
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ksgk-fy/M7Percival_010.14-0.33-0.6-0.72-0.02-0.65-7B"
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"])