A Llama Chat Model of 160M Parameters

• Base model: JackFram/llama-160m
• Datasets:
  • ehartford/wizard_vicuna_70k_unfiltered
  • totally-not-an-llm/EverythingLM-data-V3
  • Open-Orca/SlimOrca-Dedup
  • databricks/databricks-dolly-15k
  • THUDM/webglm-qa
• Availability in other ML formats:
  • GGUF: Felladrin/gguf-Llama-160M-Chat-v1
  • ONNX: Felladrin/onnx-Llama-160M-Chat-v1
  • MLC: Felladrin/mlc-q4f16-Llama-160M-Chat-v1
  • MLX: mlx-community/Llama-160M-Chat-v1-4bit-mlx

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
repetition_penalty: 1.01

Usage Example

from transformers import pipeline

generate = pipeline("text-generation", "Felladrin/Llama-160M-Chat-v1")

messages = [
    {
        "role": "system",
        "content": "You are a helpful assistant who answers user's questions with details and curiosity.",
    },
    {
        "role": "user",
        "content": "What are some potential applications for quantum computing?",
    },
]

prompt = generate.tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

output = generate(
    prompt,
    max_new_tokens=1024,
    penalty_alpha=0.5,
    top_k=4,
    repetition_penalty=1.01,
)

print(output[0]["generated_text"])

Old Open LLM Leaderboard Evaluation Results

New Open LLM Leaderboard Evaluation Results

Detailed results can be found here