• Model creator: https://huggingface.co/jan-hq/
• Original model: https://huggingface.co/jan-hq/LlamaCorn-1.1B-Chat/

Original model description:

• alignment-handbook
• generated_from_trainer
• trl
• sft
• generated_from_trainer datasets:
• jan-hq/bagel_sft_binarized
• jan-hq/dolphin_binarized
• jan-hq/openhermes_binarized
• jan-hq/bagel_dpo_binarized base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T pipeline_tag: text-generation inference: parameters: temperature: 0.7 max_new_tokens: 40 widget:
  • messages:
    • role: user content: Tell me about NVIDIA in 20 words

Model description

• Finetuned TinyLlama-1.1B further for handling simple tasks and have acceptable conversational quality
• Utilized high-quality opensource dataset
• Can be run on TensorRT-LLM on consumer devices
• Can fit into laptop dGPUs with as little as >=6gb of VRAM

Prompt template

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

Run this model

• 💻 100% offline on your machine: Your conversations remain confidential, and visible only to you.
• 🗂️ ** An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time.
• 🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints
• 🌍 Open Source & Free: We build in public; check out our Github

About Jan

LlamaCorn-1.1B-Chat

Training procedure

Training hyperparameters

• learning_rate: 5e-07
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.0

Open LLM Leaderboard Evaluation Results