Downloads · 30 days
98
5% of all-time downloads
v000000_-_NM-12B-Lyris-dev-3-gguf
RichardErkhov/v000000_-_NM-12B-Lyris-dev-3-gguf
v000000_-_NM-12B-Lyris-dev-3-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
2.1K
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 31, 2024
- Updated
- Nov 1, 2024
- SHA
- cd485a24
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
NM-12B-Lyris-dev-3 - GGUF
- Model creator: https://huggingface.co/v000000/
- Original model: https://huggingface.co/v000000/NM-12B-Lyris-dev-3/
| Name | Quant method | Size |
|---|---|---|
| NM-12B-Lyris-dev-3.Q2_K.gguf | Q2_K | 4.46GB |
| NM-12B-Lyris-dev-3.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| NM-12B-Lyris-dev-3.Q3_K.gguf | Q3_K | 5.67GB |
| NM-12B-Lyris-dev-3.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| NM-12B-Lyris-dev-3.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| NM-12B-Lyris-dev-3.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| NM-12B-Lyris-dev-3.Q4_0.gguf | Q4_0 | 6.59GB |
| NM-12B-Lyris-dev-3.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| NM-12B-Lyris-dev-3.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| NM-12B-Lyris-dev-3.Q4_K.gguf | Q4_K | 6.96GB |
| NM-12B-Lyris-dev-3.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| NM-12B-Lyris-dev-3.Q4_1.gguf | Q4_1 | 7.26GB |
| NM-12B-Lyris-dev-3.Q5_0.gguf | Q5_0 | 7.93GB |
| NM-12B-Lyris-dev-3.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| NM-12B-Lyris-dev-3.Q5_K.gguf | Q5_K | 8.13GB |
| NM-12B-Lyris-dev-3.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| NM-12B-Lyris-dev-3.Q5_1.gguf | Q5_1 | 8.61GB |
| NM-12B-Lyris-dev-3.Q6_K.gguf | Q6_K | 9.37GB |
| NM-12B-Lyris-dev-3.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-dev3-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, dev3
- 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>x2 Sequential PASS, order: 2, 4</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 31, 2024
- Updated
- Nov 1, 2024