rwkv-raven-7b.yaml

name: "rwkv-raven-7b"
license: "Apache 2.0"
urls:
- https://github.com/BlinkDL/RWKV-LM
description: |
    RWKV is an RNN with Transformer-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable).
    And it's 100% attention-free. You only need the hidden state at position t to compute the state at position t+1. 
    You can use the "GPT" mode to quickly compute the hidden state for the "RNN" mode.
    This version is quantized for ggml to work with rwkv.cpp.
config_file: |
  parameters:
    model: "Q8_0-RWKV-4-Raven-7B-v11x-Eng99-Other1-20230429-ctx8192"
    top_k: 80
    temperature: 0.9
    max_tokens: 100
    top_p: 0.8
  context_size: 1024
  backend: "rwkv"
  cutwords:
  - "Bob:.*"
  roles:
    user: "Bob:"
    system: "Alice:"
    assistant: "Alice:"
  template:
    completion: rwkv-completion
    chat: rwkv-chat
files:
- filename: "Q8_0-RWKV-4-Raven-7B-v11x-Eng99-Other1-20230429-ctx8192"
  sha256: "75d252da63405e9897bff2957f9b6b1c94d496a50e4772d5fc1ec22fb048f9b5"
  uri: "https://huggingface.co/BlinkDL/rwkv-4-raven/resolve/main/Q8_0-RWKV-4-Raven-7B-v11x-Eng99%25-Other1%25-20230429-ctx8192.bin"
- filename: "Q8_0-RWKV-4-Raven-7B-v11x-Eng99-Other1-20230429-ctx8192.tokenizer.json"
  sha256: "56ac4821e129d2c520fdaba60abd920fa852ada51b45c0dd52bbb6bd8c985ade"
  uri: "https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json"
prompt_templates:
- name: "rwkv-completion"
  content: |
    Complete the following sentence: {{.Input}} 
- name: "rwkv-chat"
  content: |
    The following is a verbose detailed conversation between Bob and a woman, Alice. Alice is intelligent, friendly and likeable. Alice is likely to agree with Bob.

    Bob: Hello Alice, how are you doing?

    Alice: Hi Bob! Thanks, I'm fine. What about you?

    Bob: I am very good! It's nice to see you. Would you mind me chatting with you for a while?

    Alice: Not at all! I'm listening.

    {{.Input}}

    Alice: