Upload 17 files
Browse files- .gitattributes +2 -0
- Nemesia-Gemma3-12B-v2.0-F16.gguf +3 -0
- README.md +62 -1
- added_tokens.json +3 -0
- config.json +62 -0
- mergekit_config.yml +18 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +29 -0
- processor_config.json +4 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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 |
+
Nemesia-Gemma3-12B-v2.0-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Nemesia-Gemma3-12B-v2.0-F16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47475dfb6837d51e8fbc960b33769aeaea73f49be0ea99113a5cd71468eae41
|
3 |
+
size 23540152096
|
README.md
CHANGED
@@ -1,3 +1,64 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- mlabonne/gemma-3-12b-it-abliterated
|
4 |
+
- google/gemma-3-12b-it
|
5 |
+
- qiuxi337/gemma-3-12b-it-grpo
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- mergekit
|
9 |
+
- merge
|
10 |
+
|
11 |
---
|
12 |
+
# temp
|
13 |
+
|
14 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
+
|
16 |
+
## Merge Details
|
17 |
+
### Merge Method
|
18 |
+
|
19 |
+
This model was merged using the NuSLERP merge method using [mlabonne/gemma-3-12b-it-abliterated](https://huggingface.co/mlabonne/gemma-3-12b-it-abliterated) as a base.
|
20 |
+
|
21 |
+
Well, it's been a while, hasn't it? It's only been a short 5 months since I posted the last Nemesia version, saying the famous last words
|
22 |
+
|
23 |
+
> I will try swapping out a model or two in the merge and trying again to upload as a v2.0.
|
24 |
+
|
25 |
+
Then, exams and university stuff crushed me whole which wasn't great, and I didn't have any time or computational resources to get back to merging on a reasonable timeframe until now.
|
26 |
+
|
27 |
+
Honestly, in the time since, Qwen2.5-7B really has not turned out to be all that interesting, Mistral Nemo stealing most of its thunder. So, I decided to update my Nemesia mergeset with a
|
28 |
+
new base: **Gemma3-12B**! In my experience, it has been alright, so I'm excited to tinker with it.
|
29 |
+
|
30 |
+
In my testing, this thing is alright- I couldn't run any GGUFs of it since I don't even know what on earth has happened to my `.venv` in the 5 months past, I'm pretty sure my Transformers installation
|
31 |
+
is corrupted, and I'm re-cloning llama.cpp as I write this. I ran the FP16 and it seemed coherent enough, but I leave that to you to decide.
|
32 |
+
|
33 |
+
Uses all of the special NuSLERP options because they're there, and is based on the abliterated version of Gemma3 instead of the base because I <3 mlabonne.
|
34 |
+
|
35 |
+
### Models Merged
|
36 |
+
|
37 |
+
The following models were included in the merge:
|
38 |
+
* [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it)
|
39 |
+
* [qiuxi337/gemma-3-12b-it-grpo](https://huggingface.co/qiuxi337/gemma-3-12b-it-grpo)
|
40 |
+
|
41 |
+
### Configuration
|
42 |
+
|
43 |
+
The following YAML configuration was used to produce this model:
|
44 |
+
|
45 |
+
```yaml
|
46 |
+
models:
|
47 |
+
- model: mlabonne/gemma-3-12b-it-abliterated
|
48 |
+
parameters:
|
49 |
+
weight: 1.0
|
50 |
+
- model: qiuxi337/gemma-3-12b-it-grpo
|
51 |
+
parameters:
|
52 |
+
weight: 0.5
|
53 |
+
- model: google/gemma-3-12b-it
|
54 |
+
parameters:
|
55 |
+
weight: 0.2
|
56 |
+
merge_method: nuslerp
|
57 |
+
base_model: mlabonne/gemma-3-12b-it-abliterated
|
58 |
+
parameters:
|
59 |
+
normalize: true
|
60 |
+
int8_mask: true
|
61 |
+
nuslerp_flatten: false
|
62 |
+
nuslerp_row_wise: true
|
63 |
+
dtype: float16
|
64 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image_soft_token>": 262144
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Gemma3ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"boi_token_index": 255999,
|
6 |
+
"eoi_token_index": 256000,
|
7 |
+
"eos_token_id": [
|
8 |
+
1,
|
9 |
+
106
|
10 |
+
],
|
11 |
+
"image_token_index": 262144,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"mm_tokens_per_image": 256,
|
14 |
+
"model_type": "gemma3",
|
15 |
+
"text_config": {
|
16 |
+
"attention_bias": false,
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"attn_logit_softcapping": null,
|
19 |
+
"cache_implementation": "hybrid",
|
20 |
+
"final_logit_softcapping": null,
|
21 |
+
"head_dim": 256,
|
22 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
23 |
+
"hidden_size": 3840,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 15360,
|
26 |
+
"max_position_embeddings": 131072,
|
27 |
+
"model_type": "gemma3_text",
|
28 |
+
"num_attention_heads": 16,
|
29 |
+
"num_hidden_layers": 48,
|
30 |
+
"num_key_value_heads": 8,
|
31 |
+
"query_pre_attn_scalar": 256,
|
32 |
+
"rms_norm_eps": 1e-06,
|
33 |
+
"rope_local_base_freq": 10000.0,
|
34 |
+
"rope_scaling": {
|
35 |
+
"factor": 8.0,
|
36 |
+
"rope_type": "linear"
|
37 |
+
},
|
38 |
+
"rope_theta": 1000000.0,
|
39 |
+
"sliding_window": 1024,
|
40 |
+
"sliding_window_pattern": 6,
|
41 |
+
"torch_dtype": "bfloat16",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 262208
|
44 |
+
},
|
45 |
+
"torch_dtype": "float16",
|
46 |
+
"transformers_version": "4.51.3",
|
47 |
+
"vision_config": {
|
48 |
+
"attention_dropout": 0.0,
|
49 |
+
"hidden_act": "gelu_pytorch_tanh",
|
50 |
+
"hidden_size": 1152,
|
51 |
+
"image_size": 896,
|
52 |
+
"intermediate_size": 4304,
|
53 |
+
"layer_norm_eps": 1e-06,
|
54 |
+
"model_type": "siglip_vision_model",
|
55 |
+
"num_attention_heads": 16,
|
56 |
+
"num_channels": 3,
|
57 |
+
"num_hidden_layers": 27,
|
58 |
+
"patch_size": 14,
|
59 |
+
"torch_dtype": "bfloat16",
|
60 |
+
"vision_use_head": false
|
61 |
+
}
|
62 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: mlabonne/gemma-3-12b-it-abliterated
|
3 |
+
parameters:
|
4 |
+
weight: 1.0
|
5 |
+
- model: qiuxi337/gemma-3-12b-it-grpo
|
6 |
+
parameters:
|
7 |
+
weight: 0.5
|
8 |
+
- model: google/gemma-3-12b-it
|
9 |
+
parameters:
|
10 |
+
weight: 0.2
|
11 |
+
merge_method: nuslerp
|
12 |
+
base_model: mlabonne/gemma-3-12b-it-abliterated
|
13 |
+
parameters:
|
14 |
+
normalize: true
|
15 |
+
int8_mask: true
|
16 |
+
nuslerp_flatten: false
|
17 |
+
nuslerp_row_wise: true
|
18 |
+
dtype: float16
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d4e87bfc31218de4b01d23a8095552e2169f3e719ead934baec60949732d171
|
3 |
+
size 4939493352
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b1c2f0c53647c22cdc719a7ef4a94a2d70d3333f451b5190f29cff55814567
|
3 |
+
size 4931296512
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3778ec3c69fa20cf3a3bb0a7fc7074b613ce945ebcf4dc31742ba3d0fbb1bcd3
|
3 |
+
size 4931296512
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c00aa65941098a39998dace46d3bdbd70d577cee56e50efcb34cbe113207a622
|
3 |
+
size 4931296512
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:976d86a5b281df8a9a8ced0ffb935540ada0d438bab2c4e839b3e54704c53465
|
3 |
+
size 4641409128
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pan_and_scan": null,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"image_mean": [
|
8 |
+
0.5,
|
9 |
+
0.5,
|
10 |
+
0.5
|
11 |
+
],
|
12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
13 |
+
"image_seq_length": 256,
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"pan_and_scan_max_num_crops": null,
|
20 |
+
"pan_and_scan_min_crop_size": null,
|
21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
22 |
+
"processor_class": "Gemma3Processor",
|
23 |
+
"resample": 2,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"height": 896,
|
27 |
+
"width": 896
|
28 |
+
}
|
29 |
+
}
|
processor_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_seq_length": 256,
|
3 |
+
"processor_class": "Gemma3Processor"
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"boi_token": "<start_of_image>",
|
3 |
+
"bos_token": {
|
4 |
+
"content": "<bos>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"eoi_token": "<end_of_image>",
|
11 |
+
"eos_token": {
|
12 |
+
"content": "<eos>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"image_token": "<image_soft_token>",
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
3 |
+
size 33384568
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
3 |
+
size 4689074
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|