|
--- |
|
base_model: |
|
- meta-llama/Llama-3.2-3B-Instruct |
|
- meta-llama/Llama-3.2-3B |
|
- PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# 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 breadcrumbs_ties merge method using [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) |
|
* [PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B](https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
merge_method: breadcrumbs_ties |
|
base_model: meta-llama/Llama-3.2-3B |
|
tokenizer_source: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
dtype: bfloat16 |
|
parameters: |
|
normalize: true |
|
models: |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: meta-llama/Llama-3.2-3B-Instruct |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
- model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B |
|
parameters: |
|
weight: 1 |
|
density: 0.9 |
|
gamma: 0.01 |
|
normalize: true |
|
int8_mask: true |
|
random_seed: 0 |
|
temperature: 0.5 |
|
top_p: 0.65 |
|
inference: true |
|
max_tokens: 999999999 |
|
stream: true |
|
quantization: |
|
method: int8 |
|
value: 100 |
|
quantization: |
|
method: int4 |
|
value: 100 |
|
|
|
``` |
|
|
