|
--- |
|
base_model: v000000/L3-11.5B-DuS-MoonRoot |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- llama |
|
- llama-cpp |
|
--- |
|
|
|
# Quants in repo: Q8_0 imatrix, static |
|
|
|
# v000000/L3-11.5B-DuS-MoonRoot-Q8_0-GGUF |
|
This model was converted to GGUF format from [`v000000/L3-11.5B-DuS-MoonRoot`](https://huggingface.co/v000000/L3-11.5B-DuS-MoonRoot) using llama.cpp |
|
Refer to the [original model card](https://huggingface.co/v000000/L3-11.5B-DuS-MoonRoot) for more details on the model.' |
|
|
|
### Llama-3-11.5B-Depth-Upscaled-MoonRoot |
|
experiemental solar-like llama3 frankenmerge, no continued finetuning |
|
|
|
 |
|
|
|
# Pretty good understanding gets the percentage wrong but understands. |
|
```bash |
|
user: A dead cat is placed into a box along with a nuclear isotope, a vial of poison and a radiation detector. |
|
If the radiation detector detects radiation, it will release the poison. The box is opened one day later. |
|
What is the probability of the cat being alive? |
|
|
|
assistant: The answer is 100%. Since the cat is already dead when it was placed in the box, |
|
there is no possibility for it to be alive when the box is opened... |
|
``` |
|
|
|
Shows similar emergent language nuance abilities compared to 8B. |
|
|
|
Unaligned and somewhat lazy. Use rep_pen 1.1 |
|
|
|
# merge |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the passthrough merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B](https://huggingface.co/Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B) |
|
* [v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
---Step 3 |
|
```yaml |
|
slices: |
|
- sources: |
|
- model: v000000/L3-8B-Poppy-Moonfall-C |
|
layer_range: [0, 24] |
|
- sources: |
|
- model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B |
|
layer_range: [8, 32] |
|
merge_method: passthrough |
|
dtype: bfloat16 |
|
|
|
``` |
|
---Step 2 |
|
```yaml |
|
slices: |
|
- sources: |
|
- model: v000000/L3-8B-Poppy-Sunspice-experiment-c+Blackroot/Llama-3-8B-Abomination-LORA |
|
layer_range: [0, 32] |
|
- model: v000000/L3-8B-Poppy-Sunspice-experiment-c+ResplendentAI/BlueMoon_Llama3 |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: v000000/L3-8B-Poppy-Sunspice-experiment-c+Blackroot/Llama-3-8B-Abomination-LORA |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0, 0.5, 0.3, 0.7, 1] |
|
- filter: mlp |
|
value: [1, 0.5, 0.7, 0.3, 0] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
random_seed: 0 |
|
|
|
``` |
|
---Step 1 |
|
```yaml |
|
models: |
|
- model: crestf411/L3-8B-sunfall-abliterated-v0.2 |
|
parameters: |
|
weight: 0.1 |
|
density: 0.18 |
|
- model: Hastagaras/HALU-8B-LLAMA3-BRSLURP |
|
parameters: |
|
weight: 0.1 |
|
density: 0.3 |
|
- model: Nitral-Archive/Poppy_Porpoise-Biomix |
|
parameters: |
|
weight: 0.1 |
|
density: 0.42 |
|
- model: cgato/L3-TheSpice-8b-v0.8.3 |
|
parameters: |
|
weight: 0.2 |
|
density: 0.54 |
|
- model: Sao10K/L3-8B-Stheno-v3.2 |
|
parameters: |
|
weight: 0.2 |
|
density: 0.66 |
|
- model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B |
|
parameters: |
|
weight: 0.3 |
|
density: 0.78 |
|
merge_method: dare_ties |
|
base_model: NousResearch/Meta-Llama-3-8B-Instruct |
|
parameters: |
|
int8_mask: true |
|
dtype: bfloat16 |
|
|
|
``` |
|
|
|
--- |
|
base_model: |
|
- Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B |
|
- v000000/L3-8B-Poppy-Moonfall-C |
|
|
|
# Prompt Template: |
|
```bash |
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|> |
|
|
|
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
{output}<|eot_id|> |
|
|
|
``` |
