Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +42 -0
- config.json +27 -0
- mergekit_config.yml +12 -0
- model-00001-of-00051.safetensors +3 -0
- model-00002-of-00051.safetensors +3 -0
- model-00003-of-00051.safetensors +3 -0
- model-00004-of-00051.safetensors +3 -0
- model-00005-of-00051.safetensors +3 -0
- model-00006-of-00051.safetensors +3 -0
- model-00007-of-00051.safetensors +3 -0
- model-00008-of-00051.safetensors +3 -0
- model-00009-of-00051.safetensors +3 -0
- model-00010-of-00051.safetensors +3 -0
- model-00011-of-00051.safetensors +3 -0
- model-00012-of-00051.safetensors +3 -0
- model-00013-of-00051.safetensors +3 -0
- model-00014-of-00051.safetensors +3 -0
- model-00015-of-00051.safetensors +3 -0
- model-00016-of-00051.safetensors +3 -0
- model-00017-of-00051.safetensors +3 -0
- model-00018-of-00051.safetensors +3 -0
- model-00019-of-00051.safetensors +3 -0
- model-00020-of-00051.safetensors +3 -0
- model-00021-of-00051.safetensors +3 -0
- model-00022-of-00051.safetensors +3 -0
- model-00023-of-00051.safetensors +3 -0
- model-00024-of-00051.safetensors +3 -0
- model-00025-of-00051.safetensors +3 -0
- model-00026-of-00051.safetensors +3 -0
- model-00027-of-00051.safetensors +3 -0
- model-00028-of-00051.safetensors +3 -0
- model-00029-of-00051.safetensors +3 -0
- model-00030-of-00051.safetensors +3 -0
- model-00031-of-00051.safetensors +3 -0
- model-00032-of-00051.safetensors +3 -0
- model-00033-of-00051.safetensors +3 -0
- model-00034-of-00051.safetensors +3 -0
- model-00035-of-00051.safetensors +3 -0
- model-00036-of-00051.safetensors +3 -0
- model-00037-of-00051.safetensors +3 -0
- model-00038-of-00051.safetensors +3 -0
- model-00039-of-00051.safetensors +3 -0
- model-00040-of-00051.safetensors +3 -0
- model-00041-of-00051.safetensors +3 -0
- model-00042-of-00051.safetensors +3 -0
- model-00043-of-00051.safetensors +3 -0
- model-00044-of-00051.safetensors +3 -0
- model-00045-of-00051.safetensors +3 -0
- model-00046-of-00051.safetensors +3 -0
- model-00047-of-00051.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# magstral-123b
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the SLERP merge method.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* mistral-large
|
22 |
+
* magnum-v2-123b
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
slices:
|
30 |
+
- sources:
|
31 |
+
- model: mistral-large
|
32 |
+
layer_range: [0, 88]
|
33 |
+
- model: magnum-v2-123b
|
34 |
+
layer_range: [0, 88]
|
35 |
+
merge_method: slerp
|
36 |
+
base_model: mistral-large
|
37 |
+
parameters:
|
38 |
+
t:
|
39 |
+
- value: 0.5
|
40 |
+
dtype: bfloat16
|
41 |
+
|
42 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "magstral-123b",
|
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": 12288,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 131072,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 96,
|
17 |
+
"num_hidden_layers": 88,
|
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": "4.44.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32768
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: mistral-large
|
4 |
+
layer_range: [0, 88]
|
5 |
+
- model: magnum-v2-123b
|
6 |
+
layer_range: [0, 88]
|
7 |
+
merge_method: slerp
|
8 |
+
base_model: mistral-large
|
9 |
+
parameters:
|
10 |
+
t:
|
11 |
+
- value: 0.5
|
12 |
+
dtype: bfloat16
|
model-00001-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83e081a91fe25bc98f3f5aecbf9a97ef2fdd9cc26da1e63f32b77a217214dd8d
|
3 |
+
size 4378928504
|
model-00002-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97bf56f54f00ae55821dda4b22e4b047371ce7a5a533064c739a0cba2e4ab0c4
|
3 |
+
size 4907411088
|
model-00003-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56ee0568fb1a76b37034b9a57d401a71e0e42c8bd52adb87467c3aff182d97da
|
3 |
+
size 4806747904
|
model-00004-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e77e654712d155747e6ac183090fb224a033389b06f54de7dd32fb9a36f02d
|
3 |
+
size 4831938544
|
model-00005-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fb9c04c1f40b2aabadfbc7a78dc8023368d44111600c39515986d73f5d8acff
|
3 |
+
size 4831938552
|
model-00006-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:965c96411cd0e0bbfd9d3931d5333f8cff663000440d833c7e24587e41c1dc92
|
3 |
+
size 4907411096
|
model-00007-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02ec9c9002669b5a3c9fb6a926a25df4ec9052bf8ff10000c5dd320b1d8833d
|
3 |
+
size 4806747904
|
model-00008-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8226b36b17f8d27c6a577015f38fc78680be198d77f87fc995e5d1982a16c2c5
|
3 |
+
size 4831938536
|
model-00009-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3abc377266be4efde8ea06ffaa3ff3f5360882cdfbcb9a84d0f4a320ffba19bd
|
3 |
+
size 4831938552
|
model-00010-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3968cd1860a7955e09b0947a4e90a33ae39bb75cc244150a6e37191f1faf1fb
|
3 |
+
size 4907411096
|
model-00011-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d5b924604b3815aad113c51b52a9f512a60c80b4c7ae8decf49e953c8040d2
|
3 |
+
size 4806747904
|
model-00012-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b333b177b3b456d7cbe1194dfaf9abc678c3e09ddfe2974c7e4862ee86a42543
|
3 |
+
size 4831938544
|
model-00013-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4161cfda8b5ab27435557abd5ea4d90e17fbbee28a0060fbc02f55867b77cd7e
|
3 |
+
size 4831938552
|
model-00014-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f781803f293cfc4a2cc173f9372bd52d4219e0a91a85967ec4f0c6bf4c26ceb2
|
3 |
+
size 4907411088
|
model-00015-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6848c95870d87eb1aa897b329f77c3fedf26d6f25acd05a4f4d04f2ec5319d3
|
3 |
+
size 4806747904
|
model-00016-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccc4e04ec7539a0150ca833fb3b411e24bcd1179d38a84b4f1d075f1400fca5f
|
3 |
+
size 4831938544
|
model-00017-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbdd30eef5e40045d27019d64b9cec23edee2d1398db0a14db9b24e3bcd16e5c
|
3 |
+
size 4831938552
|
model-00018-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066755e4a54d3ef3c852e6852855da401c1d309e3df5511ab4d7fa45de7debcf
|
3 |
+
size 4907411096
|
model-00019-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a38e2409d0b389a33292e70400f04e54abb4e917008c412a011d62055b2c730f
|
3 |
+
size 4806747904
|
model-00020-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66e49d68fdf2e9057d62ac02625adae7a3d20ea095243f32897fa943f2b18150
|
3 |
+
size 4831938544
|
model-00021-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b25ddffa6c400c28de7adf45e52fc16a7e90087d114f8c906261003e229878ed
|
3 |
+
size 4831938544
|
model-00022-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf04aced230278161b0e04a2f1e287886b9b70a393954f9ae1240126391157af
|
3 |
+
size 4907411096
|
model-00023-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:446933298e51b89961d66cf35d419656c7b3cec7453d7b65ffa26a88592989b6
|
3 |
+
size 4806747904
|
model-00024-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cd6b2c2125079ba883fd6f99d982f1bc3ef3b91ebfc163d2c2e89e4feb8686e
|
3 |
+
size 4831938544
|
model-00025-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77c0aba0f0bb3f3f128ef9d2bbda8e15bd06f6400cbc10986e13e94e9100623d
|
3 |
+
size 4831938552
|
model-00026-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a964de3a42d00d50454fb5a54a23f9463e4dbc4a26aefc44a0ffadb596d1ba93
|
3 |
+
size 4907411096
|
model-00027-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:935f3dc09afa0fefe54028babb4c619f519f015a8e6e89262757d77025d65c2d
|
3 |
+
size 4806747896
|
model-00028-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bac9886048167cfdfa10036a701f5e15578148b99d5bdb084da5ebe742341b8
|
3 |
+
size 4831938544
|
model-00029-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66eb72966211ba33fb44e933070468b19091ba6fb47c36cf57909839e238494f
|
3 |
+
size 4831938552
|
model-00030-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fad8be41f5faa07688e6367074398ddd06f3d9b47d1f69926f2ed522822c895
|
3 |
+
size 4907411096
|
model-00031-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9682f89e8a37e6bfc40ab00f7a6406cb6e764cbe71bf64e1a9ac5e7fb58b1ded
|
3 |
+
size 4806747904
|
model-00032-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e2cbb8c0f2567a3fc4eba5aef003325e8f72a8b4531727a44e5c1e65eb67f7e
|
3 |
+
size 4831938544
|
model-00033-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89324162aa8bd09f0a8e75b9b4bdc898c8a780119a5cb334ea4c137cd3f63091
|
3 |
+
size 4831938544
|
model-00034-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5daed387a422073ac5be310b9d2751e989644ced372991de8369bc2d24ac2c2
|
3 |
+
size 4907411096
|
model-00035-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a1afa93be57a3097c4e3d18f4ce5bc2979889cddf4bb1e3c4aa545e11eff029
|
3 |
+
size 4806747904
|
model-00036-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76a86b93389bbd2c18fe8730bf2dd54fa01c11036797ab86a8d779213fcfc18
|
3 |
+
size 4831938544
|
model-00037-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db0ca458567411de7dc70ec38bdc116b70fe8e4775ef803c62ae3d5934f8561b
|
3 |
+
size 4831938552
|
model-00038-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84d6e8db653105721c58383098ccae2dee76e9faa941b299a092eccd23b99af
|
3 |
+
size 4907411096
|
model-00039-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a65373370fe0b7ca81511a9658806c5f9d8fd79292567757ed66e5da08f161bd
|
3 |
+
size 4806747904
|
model-00040-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f936fe6af5a8a1c7b1b088346911174a5e852c223d590804a6c731b380f6652
|
3 |
+
size 4831938544
|
model-00041-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e6312143f6ffe605238b49f0077f94cd1e7b285a3afd502c15c837448ce56b1
|
3 |
+
size 4831938552
|
model-00042-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70f339b092bd0beae541922d3ea7f8dd1326e2bfb7e995f7f586d2ca0659a8c9
|
3 |
+
size 4907411096
|
model-00043-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f69e8d6a7018d6d51261cc3f3c72f8c0ffdf0041fbc4f1147a17fb03290b5c0
|
3 |
+
size 4806747904
|
model-00044-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d76aecfe19f046def937b7ab89d8cf77b0d52071687ef26663fad555f56f847b
|
3 |
+
size 4831938544
|
model-00045-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fb3aee639e99baf899f6d5fb38584d17c7db7252609e50b9c5e9893fb36d76b
|
3 |
+
size 4831938552
|
model-00046-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b45fad994e68d2d2c44c3e6443af33ad001f2c224ad4cd9d4ebae4483a0173c
|
3 |
+
size 4907411088
|
model-00047-of-00051.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7adfd5ef920cdf6ade28a95ae10f696450510af8cf2d1411ac52b80156224af
|
3 |
+
size 4806747904
|