MaziyarPanahi's picture
Upload folder using huggingface_hub (#1)
ff562b2 verified
|
raw
history blame
1.67 kB
---
license: apache-2.0
tags:
- Safetensors
- text-generation-inference
- merge
- transformers
- safetensors
- mistral
- text-generation
- merge
- mergekit
- lazymergekit
- automerger
- base_model:CorticalStack/shadow-clown-7B-slerp
- base_model:Gille/StrangeMerges_32-7B-slerp
- license:apache-2.0
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
model_name: M7Yamshadowexperiment28_ShadowStrangemerges_32
base_model:
- automerger/M7Yamshadowexperiment28-7B
- automerger/ShadowStrangemerges_32-7B
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# M7Yamshadowexperiment28_ShadowStrangemerges_32
M7Yamshadowexperiment28_ShadowStrangemerges_32 is a merge of the following models:
* [automerger/M7Yamshadowexperiment28-7B](https://huggingface.co/automerger/M7Yamshadowexperiment28-7B)
* [automerger/ShadowStrangemerges_32-7B](https://huggingface.co/automerger/ShadowStrangemerges_32-7B)
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "MaziyarPanahi/M7Yamshadowexperiment28_ShadowStrangemerges_32"
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"])
```