ArtusDev commited on
Commit
e725af5
·
verified ·
1 Parent(s): 24db469

Upload folder using huggingface_hub

Browse files
.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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ EtherealAurora-12B-v2.png filter=lfs diff=lfs merge=lfs -text
EtherealAurora-12B-v2.png ADDED

Git LFS Details

  • SHA256: 2a414ac454b0ad7bda4c4a9bdfa2764e02fb4fc35da496ce032206bbf1f5769e
  • Pointer size: 132 Bytes
  • Size of remote file: 2.5 MB
README.md CHANGED
@@ -1,48 +1,44 @@
1
  ---
2
- base_model: yamatazen/EtherealAurora-12B-v2
3
- base_model_relation: quantized
4
- quantized_by: ArtusDev
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
  - chatml
10
- - exl3
11
  language:
12
  - en
13
  - ja
14
  ---
 
 
 
15
 
16
- ## EXL3 Quants of yamatazen/EtherealAurora-12B-v2
17
 
18
- EXL3 quants of [yamatazen/EtherealAurora-12B-v2](https://huggingface.co/yamatazen/EtherealAurora-12B-v2) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.
 
19
 
20
- ### Quants
21
- | Quant(Revision) | Bits per Weight | Head Bits |
22
- | -------- | ---------- | --------- |
23
- | [3.0_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/3.0bpw_H6) | 3.0 | 6 |
24
- | [3.5_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/3.5bpw_H6) | 3.5 | 6 |
25
- | [4.0_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/4.0bpw_H6) | 4.0 | 6 |
26
- | [4.5_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/4.5bpw_H6) | 4.5 | 6 |
27
- | [5.0_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/5.0bpw_H6) | 5.0 | 6 |
28
- | [6.0_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/6.0bpw_H6) | 6.0 | 6 |
29
- | [8.0_H6](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/8.0bpw_H6) | 8.0 | 6 |
30
- | [8.0_H8](https://huggingface.co/ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3/tree/8.0bpw_H8) | 8.0 | 8 |
31
 
32
- ### Downloading quants with huggingface-cli
33
 
34
- <details>
35
- <summary>Click to view download instructions</summary>
 
36
 
37
- Install hugginface-cli:
38
 
39
- ```bash
40
- pip install -U "huggingface_hub[cli]"
41
- ```
42
 
43
- Download quant by targeting the specific quant revision (branch):
44
-
45
- ```
46
- huggingface-cli download ArtusDev/yamatazen_EtherealAurora-12B-v2-EXL3 --revision "5bpw_H6" --local-dir ./
47
- ```
48
- </details>
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - yamatazen/EtherealAurora-12B
4
+ - natong19/Mistral-Nemo-Instruct-2407-abliterated
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
  - chatml
 
10
  language:
11
  - en
12
  - ja
13
  ---
14
+ ![image/png](https://huggingface.co/yamatazen/EtherealAurora-12B-v2/resolve/main/EtherealAurora-12B-v2.png?download=true)
15
+ This is a ChatML model.
16
+ # merge
17
 
18
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
19
 
20
+ ## Merge Details
21
+ ### Merge Method
22
 
23
+ This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
 
 
 
 
 
 
 
 
 
 
24
 
25
+ ### Models Merged
26
 
27
+ The following models were included in the merge:
28
+ * [yamatazen/EtherealAurora-12B](https://huggingface.co/yamatazen/EtherealAurora-12B)
29
+ * [natong19/Mistral-Nemo-Instruct-2407-abliterated](https://huggingface.co/natong19/Mistral-Nemo-Instruct-2407-abliterated)
30
 
31
+ ### Configuration
32
 
33
+ The following YAML configuration was used to produce this model:
 
 
34
 
35
+ ```yaml
36
+ base_model: yamatazen/EtherealAurora-12B
37
+ models:
38
+ - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
39
+ merge_method: slerp
40
+ dtype: bfloat16
41
+ parameters:
42
+ normalize: true
43
+ t: [0.25,0.3,0.5,0.3,0.25]
44
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yamatazen/EtherealAurora-12B",
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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
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": "4.49.0",
25
+ "use_cache": false,
26
+ "vocab_size": 131072,
27
+ "quantization_config": {
28
+ "quant_method": "exl3",
29
+ "version": "0.0.3",
30
+ "bits": 2.5,
31
+ "head_bits": 6,
32
+ "calibration": {
33
+ "rows": 100,
34
+ "cols": 2048
35
+ },
36
+ "out_scales": "auto"
37
+ }
38
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ base_model: yamatazen/EtherealAurora-12B
2
+ models:
3
+ - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
4
+ merge_method: slerp
5
+ dtype: bfloat16
6
+ parameters:
7
+ normalize: true
8
+ t: [0.25,0.3,0.5,0.3,0.25]
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba2e1cdd5ef14381cc9552143d65de65bfb7db957f9c8bb0538f8a4b2ec8817
3
+ size 5261697160
quantization_config.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee57bd3271d8c200a06df40f9d7c94f8bb8f085b5cfb2d40907a794560df2ec3
3
+ size 17078342
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff