Felladrin_-_Llama-68M-Chat-v1-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-68M-Chat-v1 - bnb 4bits

• Model creator: https://huggingface.co/Felladrin/
• Original model: https://huggingface.co/Felladrin/Llama-68M-Chat-v1/

Original model description:

language:

• en license: apache-2.0 tags:
• text-generation datasets:
• THUDM/webglm-qa
• databricks/databricks-dolly-15k
• cognitivecomputations/wizard_vicuna_70k_unfiltered
• totally-not-an-llm/EverythingLM-data-V3
• Amod/mental_health_counseling_conversations
• sablo/oasst2_curated
• starfishmedical/webGPT_x_dolly
• Open-Orca/OpenOrca
• mlabonne/chatml_dpo_pairs base_model: JackFram/llama-68m widget:
• messages:
  • role: system content: You are a career counselor. The user will provide you with an individual looking for guidance in their professional life, and your task is to assist them in determining what careers they are most suited for based on their skills, interests, and experience. You should also conduct research into the various options available, explain the job market trends in different industries, and advice on which qualifications would be beneficial for pursuing particular fields.
  • role: user content: Heya!
  • role: assistant content: Hi! How may I help you?
  • role: user content: I am interested in developing a career in software engineering. What would you recommend me to do?
• messages:
  • role: system content: You are a knowledgeable assistant. Help the user as much as you can.
  • role: user content: How to become healthier?
• messages:
  • role: system content: You are a helpful assistant who provides concise responses.
  • role: user content: Hi!
  • role: assistant content: Hello there! How may I help you?
  • role: user content: I need to build a simple website. Where should I start learning about web development?
• messages:
  • role: system content: You are a very creative assistant. User will give you a task, which you should complete with all your knowledge.
  • role: user content: Write the background story of an RPG game about wizards and dragons in a sci-fi world. inference: parameters: max_new_tokens: 64 penalty_alpha: 0.5 top_k: 4 model-index:
• name: Llama-68M-Chat-v1 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: 23.29 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 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: 28.27 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 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: 25.18 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 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: 47.27 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 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: 54.3 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1 name: Open LLM Leaderboard

---

A Llama Chat Model of 68M Parameters

• Base model: JackFram/llama-68m
• Datasets:
  • THUDM/webglm-qa
  • databricks/databricks-dolly-15k
  • cognitivecomputations/wizard_vicuna_70k_unfiltered
  • totally-not-an-llm/EverythingLM-data-V3
  • Amod/mental_health_counseling_conversations
  • sablo/oasst2_curated
  • starfishmedical/webGPT_x_dolly
  • Open-Orca/OpenOrca
  • mlabonne/chatml_dpo_pairs
• Availability in other ML formats:
  • GGUF: afrideva/Llama-68M-Chat-v1-GGUF
  • ONNX: Felladrin/onnx-Llama-68M-Chat-v1

Recommended Prompt Format

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant

Recommended Inference Parameters

penalty_alpha: 0.5
top_k: 4

Open LLM Leaderboard Evaluation Results

Detailed results can be found here