jefferylovely
commited on
Commit
•
a579e74
1
Parent(s):
71fc125
Upload folder using huggingface_hub
Browse files- README.md +7 -7
- config.json +2 -4
- mergekit_config.yml +2 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- special_tokens_map.json +0 -12
- tokenizer_config.json +4 -9
README.md
CHANGED
@@ -5,14 +5,14 @@ tags:
|
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- jefferylovely/SuperThetaMaven
|
8 |
-
-
|
9 |
---
|
10 |
|
11 |
-
# jefferylovely/AiMaven-
|
12 |
|
13 |
-
jefferylovely/AiMaven-
|
14 |
* [jefferylovely/SuperThetaMaven](https://huggingface.co/jefferylovely/SuperThetaMaven)
|
15 |
-
* [
|
16 |
|
17 |
## 🧩 Configuration
|
18 |
|
@@ -21,10 +21,10 @@ slices:
|
|
21 |
- sources:
|
22 |
- model: jefferylovely/SuperThetaMaven
|
23 |
layer_range: [0, 32]
|
24 |
-
- model:
|
25 |
layer_range: [0, 32]
|
26 |
merge_method: slerp
|
27 |
-
base_model:
|
28 |
parameters:
|
29 |
t:
|
30 |
- filter: self_attn
|
@@ -44,7 +44,7 @@ from transformers import AutoTokenizer
|
|
44 |
import transformers
|
45 |
import torch
|
46 |
|
47 |
-
model = "jefferylovely/jefferylovely/AiMaven-
|
48 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
49 |
|
50 |
tokenizer = AutoTokenizer.from_pretrained(model)
|
|
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- jefferylovely/SuperThetaMaven
|
8 |
+
- flemmingmiguel/MBX-7B-v3
|
9 |
---
|
10 |
|
11 |
+
# jefferylovely/AiMaven-Prometheus
|
12 |
|
13 |
+
jefferylovely/AiMaven-Prometheus is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
14 |
* [jefferylovely/SuperThetaMaven](https://huggingface.co/jefferylovely/SuperThetaMaven)
|
15 |
+
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
|
16 |
|
17 |
## 🧩 Configuration
|
18 |
|
|
|
21 |
- sources:
|
22 |
- model: jefferylovely/SuperThetaMaven
|
23 |
layer_range: [0, 32]
|
24 |
+
- model: flemmingmiguel/MBX-7B-v3
|
25 |
layer_range: [0, 32]
|
26 |
merge_method: slerp
|
27 |
+
base_model: flemmingmiguel/MBX-7B-v3
|
28 |
parameters:
|
29 |
t:
|
30 |
- filter: self_attn
|
|
|
44 |
import transformers
|
45 |
import torch
|
46 |
|
47 |
+
model = "jefferylovely/jefferylovely/AiMaven-Prometheus"
|
48 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
49 |
|
50 |
tokenizer = AutoTokenizer.from_pretrained(model)
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -15,14 +15,12 @@
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
-
"pad_token_id": 2,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_theta": 10000.0,
|
21 |
"sliding_window": 4096,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.35.2",
|
25 |
-
"
|
26 |
-
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "flemmingmiguel/MBX-7B-v3",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
|
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_theta": 10000.0,
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.35.2",
|
24 |
+
"use_cache": false,
|
|
|
25 |
"vocab_size": 32000
|
26 |
}
|
mergekit_config.yml
CHANGED
@@ -3,10 +3,10 @@ slices:
|
|
3 |
- sources:
|
4 |
- model: jefferylovely/SuperThetaMaven
|
5 |
layer_range: [0, 32]
|
6 |
-
- model:
|
7 |
layer_range: [0, 32]
|
8 |
merge_method: slerp
|
9 |
-
base_model:
|
10 |
parameters:
|
11 |
t:
|
12 |
- filter: self_attn
|
|
|
3 |
- sources:
|
4 |
- model: jefferylovely/SuperThetaMaven
|
5 |
layer_range: [0, 32]
|
6 |
+
- model: flemmingmiguel/MBX-7B-v3
|
7 |
layer_range: [0, 32]
|
8 |
merge_method: slerp
|
9 |
+
base_model: flemmingmiguel/MBX-7B-v3
|
10 |
parameters:
|
11 |
t:
|
12 |
- filter: self_attn
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9942981696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e3820523522b91ace0c8ff9a6a09133c36617806144fbecdfdf44a2699a60f8
|
3 |
size 9942981696
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba1c7a9d45994b42fb84691fd18bf3a2ba945c95b46ca2b33b700a47ecd3971
|
3 |
size 4540516344
|
special_tokens_map.json
CHANGED
@@ -1,9 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<unk>",
|
4 |
-
"<s>",
|
5 |
-
"</s>"
|
6 |
-
],
|
7 |
"bos_token": {
|
8 |
"content": "<s>",
|
9 |
"lstrip": false,
|
@@ -18,13 +13,6 @@
|
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
-
"pad_token": {
|
22 |
-
"content": "<unk>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
},
|
28 |
"unk_token": {
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -25,21 +25,16 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
-
"additional_special_tokens": [
|
29 |
-
"<unk>",
|
30 |
-
"<s>",
|
31 |
-
"</s>"
|
32 |
-
],
|
33 |
"bos_token": "<s>",
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
"eos_token": "</s>",
|
36 |
"legacy": true,
|
37 |
-
"model_max_length":
|
38 |
-
"pad_token":
|
39 |
-
"padding_side": "right",
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
"unk_token": "<unk>",
|
44 |
-
"use_default_system_prompt":
|
45 |
}
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
29 |
"bos_token": "<s>",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": true,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": null,
|
|
|
35 |
"sp_model_kwargs": {},
|
36 |
"spaces_between_special_tokens": false,
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
}
|