---
license: cc-by-nc-4.0
language:
- en
---

![Lyra](https://huggingface.co/Sao10K/MN-12B-Lyra-v3/resolve/main/Lyra.png)



NEW V4!

fixes issues some were having?

[lyra-v4](https://huggingface.co/Sao10K/MN-12B-Lyra-v4)


---

### Automatic Approval

If you agree, please place future merges / derivatives under cc-by-nc-4.0 license. ty

---


Mistral-NeMo-12B-Lyra-v3, built on top of [Lyra-v2a2](https://huggingface.co/Sao10K/MN-12B-Lyra-v2a2), which itself was built upon [Lyra-v2a1](https://huggingface.co/Sao10K/MN-12B-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.
<br>\- Trained for 2 Epochs.
<br>\- Effective Global Batch Size: 128.
<br>\- 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.