metadata

license: apache-2.0
datasets:
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - icybee/share_gpt_90k_v1
language:
  - en
widget:
  - example_title: AmberChat
    text: How do I mount a tv to drywall safely?
    output:
      text: >-
        Mounting a TV to drywall safely is crucial to ensure the longevity of
        your TV and the wall. Here's a step-by-step guide on how to do it
        safely:
         1. Choose the right mount: Choose a mount that is compatible with your TV and the wall. Make sure the mount is rated for drywall and not just wood or concrete.
         2. Prepare the wall: Before mounting the TV, make sure the wall is clean and free from any debris or paint. Use a stud finder to locate the studs in the wall.
         3. Install the mount: Follow the manufacturer's instructions for mounting the TV to the wall. Use appropriate hardware and tools to secure the mount to the wall.
         4. Level the TV: Level the TV on the mount using a spirit level or a leveling kit provided by the mount manufacturer.
         5. Attach the TV to the mount: Attach the TV to the mount using the appropriate hardware and tools. Tighten the bolts and screws to ensure the TV is securely attached.
         6. Connect the cables: Connect the TV cables to the appropriate ports on the back of the TV and the mount.
         7. Test the mount: Test the mount to ensure it's secure and stable. Adjust the mount as needed to ensure the TV is level and secure.
         Mounting a TV to drywall safely is crucial to avoid damaging the wall or the TV. Follow these steps carefully and use appropriate tools and hardware to ensure a secure and stable installation.
  - example_title: example 2
    text: Happy is to sad as calm is to _
    output:
      text: >-
        The adjective that can be used to describe the opposite of calm is
        "anxious" or "stressed." So, from happy to sad, we can say that happy is
        to sad as calm is to anxious or stressed.
library_name: transformers
pipeline_tag: text-generation
tags:
  - nlp
  - llm

AmberChat

We present AmberChat, an instruction following model finetuned from LLM360/Amber.

Model Description

Model type: Language model with the same architecture as LLaMA-7B
Language(s) (NLP): English
License: Apache 2.0
Resources for more information:
- Metrics
- Fully processed Amber pretraining data

Loading AmberChat

from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberChat")
model = LlamaForCausalLM.from_pretrained("LLM360/AmberChat")

input_text = "How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids

outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

AmberChat Finetuning Details

DataMix

Subset	Number of rows	License
WizardLM/WizardLM_evol_instruct_V2_196k	143k
icybee/share_gpt_90k_v1	90k	cc0-1.0
Total	233k

Hyperparameters

Hyperparameter	Value
Total Parameters	6.7B
Hidden Size	4096
Intermediate Size (MLPs)	11008
Number of Attention Heads	32
Number of Hidden Lyaers	32
RMSNorm ɛ	1e^-6
Max Seq Length	2048
Vocab Size	32000

Evaluation

Model	MT-Bench
LLM360/Amber 359	2.48750
LLM360/AmberChat	5.428125

Citation

BibTeX:

@article{xxx,
  title={XXX},
  author={XXX},
  journal={XXX},
  year={2023}
}