Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Lyra

Mistral-NeMo-12B-Lyra-v4, a variation of Lyra-v4a1, layered over Lyra-v3, which was built on top of Lyra-v2a2, which itself was built upon Lyra-v2a1.

Automatic Approval

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


Model Versioning

[See Previous Models]
  |
Lyra-v4a1
  |
  ------------> Lyra-v4 [Seperate RL Step targeting Instruct and Coherency over Base Nemo instead of SFT First, Result is Merged with Lyra-v4a1, fixes most quant-based issues. Somehow.]

This uses ChatML, or any of its variants which were included in previous versions.


<|im_start|>system
This is the system prompt.<|im_end|>
<|im_start|>user
Instructions placed here.<|im_end|>
<|im_start|>assistant
The model's response will be here.<|im_end|>
--------------------------------------------------
[INST]system
This is another system prompt.[/INST]
[INST]user
Your instructions placed here.[/INST]
[INST]assistant
The model's response will be here.[/INST]

Recommended Samplers:

Temperature: 0.6 - 1 # Make sure min_p is set before Temperature in Sampler Orders
min_p: 0.1 - 0.2 # Crucial for NeMo

Recommended Stopping Strings:

<|im_end|>
</s>
[/INST]

Notes

- I think I fixed the extra token stuff some users seem to be facing, while retaining everything else? It's some error alright.
- If you're using XML tags, you may see weird malformed stopping strings. Just add them to your current list. and move on.
- Its pretty nice, imo. I've been messing around with it a lot.
- Make sure the ChatML template is correct, I think there's some issues with the one used in SillyTavern which might cause improper replies?


Reup due to issues I faced on my page, crashing every time i go in here. works fine now? so yay?

Changes: Weights are the same, literally. go and check the checksum.
Credit to ArliAI for the model tokenizer configs and json I yoinked, to fix the tokenizer mess (in v3) I made, hence why config.json had their model name.
Same stuff applies
Downloads last month
245
Safetensors
Model size
12.2B params
Tensor type
BF16
ยท
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Sao10K/MN-12B-Lyra-v4

Finetunes
2 models
Merges
3 models
Quantizations
27 models

Spaces using Sao10K/MN-12B-Lyra-v4 2