Downloads · 30 days
34
2% of all-time downloads
v000000_-_NM-12B-Lyris-dev-2-gguf
RichardErkhov/v000000_-_NM-12B-Lyris-dev-2-gguf
v000000_-_NM-12B-Lyris-dev-2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.9K
Public
Repo size
124 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf147 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024
- SHA
- c31dd892
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
NM-12B-Lyris-dev-2 - GGUF
- Model creator: https://huggingface.co/v000000/
- Original model: https://huggingface.co/v000000/NM-12B-Lyris-dev-2/
| Name | Quant method | Size |
|---|---|---|
| NM-12B-Lyris-dev-2.Q2_K.gguf | Q2_K | 4.46GB |
| NM-12B-Lyris-dev-2.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| NM-12B-Lyris-dev-2.Q3_K.gguf | Q3_K | 5.67GB |
| NM-12B-Lyris-dev-2.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| NM-12B-Lyris-dev-2.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| NM-12B-Lyris-dev-2.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| NM-12B-Lyris-dev-2.Q4_0.gguf | Q4_0 | 6.59GB |
| NM-12B-Lyris-dev-2.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| NM-12B-Lyris-dev-2.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| NM-12B-Lyris-dev-2.Q4_K.gguf | Q4_K | 6.96GB |
| NM-12B-Lyris-dev-2.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| NM-12B-Lyris-dev-2.Q4_1.gguf | Q4_1 | 7.26GB |
| NM-12B-Lyris-dev-2.Q5_0.gguf | Q5_0 | 7.93GB |
| NM-12B-Lyris-dev-2.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| NM-12B-Lyris-dev-2.Q5_K.gguf | Q5_K | 8.13GB |
| NM-12B-Lyris-dev-2.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| NM-12B-Lyris-dev-2.Q5_1.gguf | Q5_1 | 8.61GB |
| NM-12B-Lyris-dev-2.Q6_K.gguf | Q6_K | 9.37GB |
| NM-12B-Lyris-dev-2.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- Sao10K/MN-12B-Lyra-v1
- Sao10K/MN-12B-Lyra-v3
- unsloth/Mistral-Nemo-Instruct-2407 library_name: transformers tags:
- merge
- mistral license: cc-by-nc-4.0
Lyris-dev2-Mistral-Nemo-12B-2407
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 <b>Base</b>
- Sao10K/MN-12B-Lyra-v3 <b>x2 Sequential PASS, order: 1, 3</b>
- unsloth/Mistral-Nemo-Instruct-2407 <b>x1 Single PASS, order: 2</b>
- with z0.0001 value
<b>Prompt format:</b>
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]
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024