Kquant03_-_DolphinHermesPro-ModelStock-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

DolphinHermesPro-ModelStock - bnb 8bits

• Model creator: https://huggingface.co/Kquant03/
• Original model: https://huggingface.co/Kquant03/DolphinHermesPro-ModelStock/

Original model description:

tags:

• merge
• mergekit
• lazymergekit license: apache-2.0 thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/Jmu5DHPZwv4so5Tn-xkIO.png"

---

DolphinHermesPro-ModelStock

DolphinHermesPro-ModelStock is a merge of the following models using LazyMergekit:

models:
  - model: cognitivecomputations/dolphin-2.8-experiment26-7b
  - model: NousResearch/Hermes-2-Pro-Mistral-7B
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kquant03/DolphinHermesPro-ModelStock"
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"])