Upload folder using huggingface_hub
Browse files- README.md +46 -0
- config.json +31 -0
- mergekit_config.yml +16 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- memevis/bl0
|
| 4 |
+
- memevis/bl1
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- mergekit
|
| 8 |
+
- merge
|
| 9 |
+
|
| 10 |
+
---
|
| 11 |
+
# merge
|
| 12 |
+
|
| 13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 14 |
+
|
| 15 |
+
## Merge Details
|
| 16 |
+
### Merge Method
|
| 17 |
+
|
| 18 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [memevis/bl1](https://huggingface.co/memevis/bl1) as a base.
|
| 19 |
+
|
| 20 |
+
### Models Merged
|
| 21 |
+
|
| 22 |
+
The following models were included in the merge:
|
| 23 |
+
* [memevis/bl0](https://huggingface.co/memevis/bl0)
|
| 24 |
+
|
| 25 |
+
### Configuration
|
| 26 |
+
|
| 27 |
+
The following YAML configuration was used to produce this model:
|
| 28 |
+
|
| 29 |
+
```yaml
|
| 30 |
+
models:
|
| 31 |
+
- model: memevis/bl0
|
| 32 |
+
parameters:
|
| 33 |
+
density: 0.5
|
| 34 |
+
weight: 0.5
|
| 35 |
+
- model: memevis/bl1
|
| 36 |
+
parameters:
|
| 37 |
+
density: 0.5
|
| 38 |
+
weight: 0.5
|
| 39 |
+
|
| 40 |
+
merge_method: ties
|
| 41 |
+
base_model: memevis/bl1
|
| 42 |
+
parameters:
|
| 43 |
+
normalize: true
|
| 44 |
+
int8_mask: true
|
| 45 |
+
dtype: float16
|
| 46 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 2048,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 16,
|
| 20 |
+
"pad_token_id": 100257,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float16",
|
| 27 |
+
"transformers_version": "4.51.1",
|
| 28 |
+
"unsloth_version": "2025.3.19",
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 100263
|
| 31 |
+
}
|
mergekit_config.yml
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
models:
|
| 2 |
+
- model: memevis/bl0
|
| 3 |
+
parameters:
|
| 4 |
+
density: 0.5
|
| 5 |
+
weight: 0.5
|
| 6 |
+
- model: memevis/bl1
|
| 7 |
+
parameters:
|
| 8 |
+
density: 0.5
|
| 9 |
+
weight: 0.5
|
| 10 |
+
|
| 11 |
+
merge_method: ties
|
| 12 |
+
base_model: memevis/bl1
|
| 13 |
+
parameters:
|
| 14 |
+
normalize: true
|
| 15 |
+
int8_mask: true
|
| 16 |
+
dtype: float16
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3d9983b255a7a1c753451e7c11ce1ca11d723ae5e5ca93aa9004962b30fee44
|
| 3 |
+
size 914118816
|