Statuo / MN-12b-Lyra-v3-4bpw

huggingface.co
Total runs: 4
24-hour runs: 0
7-day runs: 0
30-day runs: 3
Model's Last Updated: August 29 2024

Introduction of MN-12b-Lyra-v3-4bpw

Model Details of MN-12b-Lyra-v3-4bpw

Sao blesses us with another Lyra MN finetune. V2 is my daily driver currently so I'm aching to get this.
This is the 4bpw EXL2 Quant of this model. You can find the original model here.
For the 8bpw version, go here
For the 6bpw version, go here

Lyra

Ungated. Thanks for the patience!

Mistral-NeMo-12B-Lyra-v3, built on top of Lyra-v2a2 , which itself was built upon Lyra-v2a1 .

Model Versioning

Lyra-v1 [Merge of Custom Roleplay & Instruct Trains, on Different Formats]
  |
  | [Additional SFT on 10% of Previous Data, Mixed]
  v
Lyra-v2a1 
  |
  | [Low Rank SFT Step + Tokenizer Diddling]
  v
Lyra-v2a2
  |
  | [RL Step Performed on Multiturn Sets, Magpie-style Responses by Lyra-v2a2 for Rejected Data]
  v
Lyra-v3

This uses a custom ChatML-style prompting Format!

-> What can go wrong?

[INST]system
This is the system prompt.[/INST]
[INST]user
Instructions placed here.[/INST]
[INST]assistant
The model's response will be here.[/INST]

Why this? I had used the wrong configs by accident. The format was meant for an 8B pruned NeMo train, instead it went to this. Oops.

Recommended Samplers:

Temperature: 0.7 - 1.2
min_p: 0.1 - 0.2 # Crucial for NeMo

Recommended Stopping Strings:

<|im_end|>
</s>

Blame messed up Training Configs, oops?

Training Metrics:

- Trained on 4xH100 SXM for 6 Hours.
- Trained for 2 Epochs.
- Effective Global Batch Size: 128.
- Dataset Used: A custom, cleaned mix of Stheno-v3.4's Dataset, focused mainly on multiturn.


Extras

Image Source: AI-Generated with FLUX.1 Dev.

have a nice day.

Runs of Statuo MN-12b-Lyra-v3-4bpw on huggingface.co

4
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
3
30-day runs

More Information About MN-12b-Lyra-v3-4bpw huggingface.co Model

More MN-12b-Lyra-v3-4bpw license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

MN-12b-Lyra-v3-4bpw huggingface.co

MN-12b-Lyra-v3-4bpw huggingface.co is an AI model on huggingface.co that provides MN-12b-Lyra-v3-4bpw's model effect (), which can be used instantly with this Statuo MN-12b-Lyra-v3-4bpw model. huggingface.co supports a free trial of the MN-12b-Lyra-v3-4bpw model, and also provides paid use of the MN-12b-Lyra-v3-4bpw. Support call MN-12b-Lyra-v3-4bpw model through api, including Node.js, Python, http.

MN-12b-Lyra-v3-4bpw huggingface.co Url

https://huggingface.co/Statuo/MN-12b-Lyra-v3-4bpw

Statuo MN-12b-Lyra-v3-4bpw online free

MN-12b-Lyra-v3-4bpw huggingface.co is an online trial and call api platform, which integrates MN-12b-Lyra-v3-4bpw's modeling effects, including api services, and provides a free online trial of MN-12b-Lyra-v3-4bpw, you can try MN-12b-Lyra-v3-4bpw online for free by clicking the link below.

Statuo MN-12b-Lyra-v3-4bpw online free url in huggingface.co:

https://huggingface.co/Statuo/MN-12b-Lyra-v3-4bpw

MN-12b-Lyra-v3-4bpw install

MN-12b-Lyra-v3-4bpw is an open source model from GitHub that offers a free installation service, and any user can find MN-12b-Lyra-v3-4bpw on GitHub to install. At the same time, huggingface.co provides the effect of MN-12b-Lyra-v3-4bpw install, users can directly use MN-12b-Lyra-v3-4bpw installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

MN-12b-Lyra-v3-4bpw install url in huggingface.co:

https://huggingface.co/Statuo/MN-12b-Lyra-v3-4bpw

Url of MN-12b-Lyra-v3-4bpw

MN-12b-Lyra-v3-4bpw huggingface.co Url

Provider of MN-12b-Lyra-v3-4bpw huggingface.co

Statuo
ORGANIZATIONS

Other API from Statuo