RichardErkhov/MaziyarPanahi_-_Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1 - bnb 8bits

• Model creator: https://huggingface.co/MaziyarPanahi/
• Original model: https://huggingface.co/MaziyarPanahi/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1/

Original model description:

license: apache-2.0 tags: - Safetensors - mistral - text-generation-inference - merge - mistral - 7b - mistralai/Mistral-7B-Instruct-v0.1 - NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3 - transformers - pytorch - mistral - text-generation - bg - ca - cs - da - de - en - es - fr - hr - hu - it - nl - pl - pt - ro - ru - sl - sr - sv - uk - dataset:Open-Orca/OpenOrca - dataset:OpenAssistant/oasst_top1_2023-08-25 - arxiv:2309.17453 - arxiv:2205.14135 - license:apache-2.0 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us

Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1

Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1 is a merge of the following models:

• mistralai/Mistral-7B-Instruct-v0.1
• NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3

🧩 Configuration

slices:
  - sources:
      - model: mistralai/Mistral-7B-Instruct-v0.1
        layer_range: [0, 32]
      - model: NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-Instruct-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "MaziyarPanahi/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v3-Mistral-7B-Instruct-v0.1"
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"])