MrRobotoAI
commited on
Commit
•
edbdd13
1
Parent(s):
7c288d3
Upload folder using huggingface_hub
Browse files- README.md +7 -7
- config.json +15 -4
- mergekit_config.yml +3 -3
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- special_tokens_map.json +5 -7
- tokenizer_config.json +7 -6
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
-
|
4 |
-
- MrRobotoAI/
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
@@ -20,8 +20,8 @@ This model was merged using the SLERP merge method.
|
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
-
* [
|
24 |
-
* [MrRobotoAI/
|
25 |
|
26 |
### Configuration
|
27 |
|
@@ -30,12 +30,12 @@ The following YAML configuration was used to produce this model:
|
|
30 |
```yaml
|
31 |
slices:
|
32 |
- sources:
|
33 |
-
- model: MrRobotoAI/
|
34 |
layer_range: [0, 32]
|
35 |
-
- model:
|
36 |
layer_range: [0, 32]
|
37 |
merge_method: slerp
|
38 |
-
base_model:
|
39 |
parameters:
|
40 |
t:
|
41 |
- filter: self_attn
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
+
- MrRobotoAI/Hathor-2
|
4 |
+
- MrRobotoAI/Hathor-6
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
|
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
+
* [MrRobotoAI/Hathor-2](https://huggingface.co/MrRobotoAI/Hathor-2)
|
24 |
+
* [MrRobotoAI/Hathor-6](https://huggingface.co/MrRobotoAI/Hathor-6)
|
25 |
|
26 |
### Configuration
|
27 |
|
|
|
30 |
```yaml
|
31 |
slices:
|
32 |
- sources:
|
33 |
+
- model: MrRobotoAI/Hathor-6
|
34 |
layer_range: [0, 32]
|
35 |
+
- model: MrRobotoAI/Hathor-2
|
36 |
layer_range: [0, 32]
|
37 |
merge_method: slerp
|
38 |
+
base_model: MrRobotoAI/Hathor-2
|
39 |
parameters:
|
40 |
t:
|
41 |
- filter: self_attn
|
config.json
CHANGED
@@ -1,9 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -11,16 +15,23 @@
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
"max_position_embeddings": 32768,
|
|
|
14 |
"model_type": "mistral",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
-
"
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.41.0",
|
24 |
-
"use_cache":
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "MrRobotoAI/Hathor-2",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "NousResearch/Yarn-Mistral-7b-128k--configuration_mistral.MistralConfig",
|
9 |
+
"AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-128k--modeling_mistral_yarn.MistralForCausalLM"
|
10 |
+
},
|
11 |
"bos_token_id": 1,
|
12 |
"eos_token_id": 2,
|
13 |
"hidden_act": "silu",
|
|
|
15 |
"initializer_range": 0.02,
|
16 |
"intermediate_size": 14336,
|
17 |
"max_position_embeddings": 32768,
|
18 |
+
"max_sequence_length": 131072,
|
19 |
"model_type": "mistral",
|
20 |
"num_attention_heads": 32,
|
21 |
"num_hidden_layers": 32,
|
22 |
"num_key_value_heads": 8,
|
23 |
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": {
|
25 |
+
"factor": 16.0,
|
26 |
+
"finetuned": true,
|
27 |
+
"original_max_position_embeddings": 8192,
|
28 |
+
"type": "yarn"
|
29 |
+
},
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"sliding_window": 131072,
|
32 |
"tie_word_embeddings": false,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
"transformers_version": "4.41.0",
|
35 |
+
"use_cache": true,
|
36 |
"vocab_size": 32000
|
37 |
}
|
mergekit_config.yml
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
slices:
|
2 |
- sources:
|
3 |
-
- model: MrRobotoAI/
|
4 |
layer_range: [0, 32]
|
5 |
-
- model:
|
6 |
layer_range: [0, 32]
|
7 |
merge_method: slerp
|
8 |
-
base_model:
|
9 |
parameters:
|
10 |
t:
|
11 |
- filter: self_attn
|
|
|
1 |
slices:
|
2 |
- sources:
|
3 |
+
- model: MrRobotoAI/Hathor-6
|
4 |
layer_range: [0, 32]
|
5 |
+
- model: MrRobotoAI/Hathor-2
|
6 |
layer_range: [0, 32]
|
7 |
merge_method: slerp
|
8 |
+
base_model: MrRobotoAI/Hathor-2
|
9 |
parameters:
|
10 |
t:
|
11 |
- filter: self_attn
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4886547008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b22c79b24a3d6cbecc4d2462108657a7c507b582b1457818ce3e32379eb7e1c7
|
3 |
size 4886547008
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a454b27b6191e7b93751504d0f1ef47ec4aa6536990a12dcd642328cc80b565
|
3 |
size 4915916176
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4681034848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef587d0fd623b4db586526d413fa337bcc31226caea2efc0d087d06711d3bd2c
|
3 |
size 4681034848
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,9 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
@@ -13,13 +18,6 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
"bos_token": {
|
8 |
"content": "<s>",
|
9 |
"lstrip": false,
|
|
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -28,17 +27,19 @@
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
|
|
|
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
-
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
-
"pad_token":
|
38 |
-
"padding_side": "right",
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
"unk_token": "<unk>",
|
43 |
-
"use_default_system_prompt":
|
44 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
"bos_token": "<s>",
|
|
|
36 |
"clean_up_tokenization_spaces": false,
|
37 |
"eos_token": "</s>",
|
|
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
+
"pad_token": null,
|
|
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": true
|
45 |
}
|