Hermes-2-Pro-11B
Hermes-2-Pro-11B is a merge of the following models using LazyMergekit:
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
- NousResearch/Hermes-2-Pro-Mistral-7B
𧩠Configuration
slices:
- sources:
- layer_range: [0, 5]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [3, 8]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [6, 11]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [9, 14]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [12, 17]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [15, 20]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [18, 23]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [21, 26]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [24, 29]
model: NousResearch/Hermes-2-Pro-Mistral-7B
- sources:
- layer_range: [27, 32]
model: NousResearch/Hermes-2-Pro-Mistral-7B
merge_method: passthrough
dtype: bfloat16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mattshumer/Hermes-2-Pro-11B"
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"])
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.