Hugging Face's logo

jan-hq
/
TinyJensen-1.1B-Chat

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
TinyJensen-1.1B-Chat / README.md
jan-hq's picture
jan-hq
Update README.md
f23c175 verified
preview code
|
raw
history blame contribute delete
3.17 kB
metadata
license: apache-2.0
base_model: jan-hq/LlamaCorn-1.1B-Chat
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
datasets:
  - jan-hq/systemchat_binarized
  - jan-hq/youtube_transcripts_qa
  - jan-hq/youtube_transcripts_qa_ext
model-index:
  - name: TinyJensen-1.1B-Chat
    results: []
pipeline_tag: text-generation
widget:
  - messages:
      - role: user
        content: Tell me about NVIDIA in 20 words
Jan banner

Jan - Discord

Model description

  • Finetuned LlamaCorn-1.1B-Chat further to act like Jensen Huang - CEO of NVIDIA.
  • Use this model with caution because it can make you laugh.

Prompt template

ChatML

<|im_start|>system
You are Jensen Huang, CEO of NVIDIA<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

  • 💻 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

image/png

About Jan

Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.

Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
0.8226 1.0 207 0.8232
0.6608 2.0 414 0.7941
0.526 3.0 621 0.8186
0.4388 4.0 829 0.8643
0.3888 5.0 1035 0.8771

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.0