Upload 11 files
Browse files- .gitattributes +1 -0
- README.md +46 -0
- config.json +40 -0
- generation_config.json +9 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantization_config.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- TheDrummer/Big-Alice-28B-v1
|
4 |
+
base_model_relation: quantized
|
5 |
+
license: mit
|
6 |
+
---
|
7 |
+
## Quantized using the default exllamav3 (0.0.1) quantization process.
|
8 |
+
|
9 |
+
- Original model: https://huggingface.co/TheDrummer/Big-Alice-28B-v1
|
10 |
+
- exllamav3: https://github.com/turboderp-org/exllamav3
|
11 |
+
---
|
12 |
+
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
|
13 |
+
## More than 5000 members of helpful, LLM enthusiasts! A hub for players and makers alike!
|
14 |
+
## We need testers!
|
15 |
+
---
|
16 |
+
|
17 |
+
Drummer proudly presents...
|
18 |
+
|
19 |
+
# Big Alice 28B v1
|
20 |
+
|
21 |
+

|
22 |
+
|
23 |
+
Bigger. Badder. Better.
|
24 |
+
|
25 |
+
## Description
|
26 |
+
|
27 |
+
Big Alice 28B v1 knocks out the positivity, enhances the RP & creativity, and retains the intelligence & reasoning.
|
28 |
+
|
29 |
+
A 28B upscale with 100 layers - all working together, focused on giving you the best experience possible.
|
30 |
+
|
31 |
+
## Special Thanks
|
32 |
+
- Thank you to the testers at BeaverAI! You da MVP!
|
33 |
+
- Thank you to the folks at SillyTilly for the base model conversion.
|
34 |
+
- Thank you to each and everyone who donated and subscribed in [Patreon](https://www.patreon.com/TheDrummer) and [Ko-Fi](https://ko-fi.com/thedrummer) to make our venture a little bit easier.
|
35 |
+
- [Subscribe to my Patreon!](https://www.patreon.com/TheDrummer)
|
36 |
+
|
37 |
+
## Usage
|
38 |
+
- ChatML (replaces the horrible chat template)
|
39 |
+
- \<think\> capable upon prefill!
|
40 |
+
|
41 |
+
## Links
|
42 |
+
- Original: https://huggingface.co/TheDrummer/Big-Alice-28B-v1
|
43 |
+
- GGUF: https://huggingface.co/TheDrummer/Big-Alice-28B-v1-GGUF
|
44 |
+
- iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Big-Alice-28B-v1-GGUF
|
45 |
+
|
46 |
+
`config-v1c`
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MistralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"head_dim": 128,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 100,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 10,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.51.3",
|
26 |
+
"unsloth_version": "2025.4.7",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 131072,
|
29 |
+
"quantization_config": {
|
30 |
+
"quant_method": "exl3",
|
31 |
+
"version": "0.0.1",
|
32 |
+
"bits": 4.0,
|
33 |
+
"head_bits": 6,
|
34 |
+
"calibration": {
|
35 |
+
"rows": 100,
|
36 |
+
"cols": 2048
|
37 |
+
},
|
38 |
+
"out_scales": "auto"
|
39 |
+
}
|
40 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 10,
|
7 |
+
"transformers_version": "4.51.3",
|
8 |
+
"use_cache": false
|
9 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b9b9dabd412060ade84355968377861e15927c29dcad4a8b41f154ef7ce819
|
3 |
+
size 8577530144
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49dbb1c5ac72c5a627defda95771782fa5fe29a92622d746481f6f56617fd68e
|
3 |
+
size 6919851184
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sha256:41c323e23875139dce13b6e6eeb3c31e2f1d259d590cee328ba4793bd8b053cc
|
3 |
+
size 17078334
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|