Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- Behemoth-v1.2-Magnum-v4-123B.png +3 -0
- README.md +47 -0
- config.json +38 -0
- mergekit_config.yml +8 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantization_config.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Behemoth-v1.2-Magnum-v4-123B.png filter=lfs diff=lfs merge=lfs -text
|
Behemoth-v1.2-Magnum-v4-123B.png
ADDED
![]() |
Git LFS Details
|
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- TheDrummer/Behemoth-123B-v1.2
|
4 |
+
- anthracite-org/magnum-v4-123b
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
license: other
|
10 |
+
license_name: mrl
|
11 |
+
inference: false
|
12 |
+
license_link: https://mistral.ai/licenses/MRL-0.1.md
|
13 |
+
|
14 |
+
---
|
15 |
+

|
16 |
+
|
17 |
+
# The Drummer becomes hornier (again)
|
18 |
+
|
19 |
+
A worthy successor as the v2 didn't set the expectations. SLERPd with less magnum as some people have reported it's being too horny and maybe less coherent.
|
20 |
+
|
21 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/arcee-ai/mergekit).
|
22 |
+
|
23 |
+
## Merge Details
|
24 |
+
### Merge Method
|
25 |
+
|
26 |
+
This model was merged using the SLERP merge method.
|
27 |
+
|
28 |
+
### Models Merged
|
29 |
+
|
30 |
+
The following models were included in the merge:
|
31 |
+
* [TheDrummer/Behemoth-123B-v1.2](https://huggingface.co/TheDrummer/Behemoth-123B-v1.2)
|
32 |
+
* [anthracite-org/magnum-v4-123b](https://huggingface.co/anthracite-org/magnum-v4-123b)
|
33 |
+
|
34 |
+
### Configuration
|
35 |
+
|
36 |
+
The following YAML configuration was used to produce this model:
|
37 |
+
|
38 |
+
```yaml
|
39 |
+
models:
|
40 |
+
- model: TheDrummer/Behemoth-123B-v1.2
|
41 |
+
- model: anthracite-org/magnum-v4-123b
|
42 |
+
merge_method: slerp
|
43 |
+
base_model: TheDrummer/Behemoth-123B-v1.2
|
44 |
+
parameters:
|
45 |
+
t: [0.1, 0.2, 0.4, 0.2, 0.1]
|
46 |
+
dtype: bfloat16
|
47 |
+
```
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TheDrummer/Behemoth-123B-v1.2",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 12288,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 131072,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 96,
|
17 |
+
"num_hidden_layers": 88,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.46.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32768,
|
27 |
+
"quantization_config": {
|
28 |
+
"quant_method": "exl3",
|
29 |
+
"version": "0.0.2",
|
30 |
+
"bits": 1.4,
|
31 |
+
"head_bits": 4,
|
32 |
+
"calibration": {
|
33 |
+
"rows": 100,
|
34 |
+
"cols": 2048
|
35 |
+
},
|
36 |
+
"out_scales": "auto"
|
37 |
+
}
|
38 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: TheDrummer/Behemoth-123B-v1.2
|
3 |
+
- model: anthracite-org/magnum-v4-123b
|
4 |
+
merge_method: slerp
|
5 |
+
base_model: TheDrummer/Behemoth-123B-v1.2
|
6 |
+
parameters:
|
7 |
+
t: [0.1, 0.2, 0.4, 0.2, 0.1]
|
8 |
+
dtype: bfloat16
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d354a7943e8fb0cf1a1604582dae50d8ad3fe3e17616d47ab74a7a1aa2759fca
|
3 |
+
size 8561310976
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ba7a618f94b4431b3990de42d7a1cc568606c675ef554174adbc945c6ba2c46
|
3 |
+
size 8499741600
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21007f89551f477c8e512252a7a9862da43f59ca2044b96a34f7f07f7f3cf027
|
3 |
+
size 5284928512
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quantization_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
3 |
+
size 587583
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|