harborwater_-_open-llama-3b-claude-30k-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

open-llama-3b-claude-30k - bnb 4bits

• Model creator: https://huggingface.co/harborwater/
• Original model: https://huggingface.co/harborwater/open-llama-3b-claude-30k/

Original model description:

language:

• en license: apache-2.0 library_name: transformers datasets:
• Norquinal/claude_multiround_chat_30k model-index:
• name: open-llama-3b-claude-30k results:
  • task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
    • type: acc_norm value: 41.72 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
    • type: acc_norm value: 72.64 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
    • type: acc value: 24.03 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
    • type: mc2 value: 38.46 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
    • type: acc value: 66.54 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 2.2 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=harborwater/open-llama-3b-claude-30k name: Open LLM Leaderboard

---

Trained on 3 epoch of the Norquinal's claude_multiround_chat_30k dataset.

note: this is another expeiment feel free to give it a try!

Prompt template:

### HUMAN:
{prompt}

### RESPONSE:
<leave a newline for the model to answer>

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here