Edit model card

Lyris-dev2-Mistral-Nemo-12B-2407

image/png EXPERIMENTAL

attempt to fix Sao10k's Lyra-V3 prompt format and stop token >and boost smarts. with strategic LATCOS vector similarity merging

prototype, unfinished but works? Sometimes it does go on forever but it's way more useable, seems to have learnt to output stop token most of the time. But it's still pretty borked especially if greeting message is long. It needs even more Nemo-Instruct-2407 merged in.

  • Sao10K/MN-12B-Lyra-v1 Base
  • Sao10K/MN-12B-Lyra-v3 x2 Sequential PASS, order: 1, 3
  • unsloth/Mistral-Nemo-Instruct-2407 x1 Single PASS, order: 2
  • with z0.0001 value

Prompt format:

Mistral Instruct

[INST] System Message [/INST]

[INST] Name: Let's get started. Please respond based on the information and instructions provided above. [/INST]

<s>[INST] Name: What is your favourite condiment? [/INST]
AssistantName: Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> 
[INST] Name: Do you have mayonnaise recipes? [/INST]
Downloads last month
33
Safetensors
Model size
12.2B params
Tensor type
FP16
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Model tree for v000000/NM-12B-Lyris-dev-2