danielhanchen
commited on
Commit
•
985e58a
1
Parent(s):
e4b558e
Upload LlamaForCausalLM
Browse files- config.json +14 -4
- generation_config.json +1 -1
- model-00001-of-00030.safetensors +1 -1
- model-00002-of-00030.safetensors +1 -1
- model-00003-of-00030.safetensors +1 -1
- model-00004-of-00030.safetensors +1 -1
- model-00005-of-00030.safetensors +1 -1
- model-00006-of-00030.safetensors +1 -1
- model-00007-of-00030.safetensors +1 -1
- model-00008-of-00030.safetensors +1 -1
- model-00009-of-00030.safetensors +1 -1
- model-00010-of-00030.safetensors +1 -1
- model-00011-of-00030.safetensors +1 -1
- model-00012-of-00030.safetensors +1 -1
- model-00013-of-00030.safetensors +1 -1
- model-00014-of-00030.safetensors +1 -1
- model-00015-of-00030.safetensors +1 -1
- model-00016-of-00030.safetensors +1 -1
- model-00017-of-00030.safetensors +1 -1
- model-00018-of-00030.safetensors +1 -1
- model-00019-of-00030.safetensors +1 -1
- model-00020-of-00030.safetensors +1 -1
- model-00021-of-00030.safetensors +1 -1
- model-00022-of-00030.safetensors +1 -1
- model-00023-of-00030.safetensors +1 -1
- model-00024-of-00030.safetensors +1 -1
- model-00025-of-00030.safetensors +1 -1
- model-00026-of-00030.safetensors +1 -1
- model-00027-of-00030.safetensors +1 -1
- model-00028-of-00030.safetensors +1 -1
- model-00029-of-00030.safetensors +1 -1
- model-00030-of-00030.safetensors +1 -1
config.json
CHANGED
@@ -1,17 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "mattshumer/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 8192,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 28672,
|
14 |
-
"max_position_embeddings":
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 64,
|
@@ -19,7 +23,13 @@
|
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
-
"rope_scaling":
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mattshumer/ref_70_e3",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
"hidden_act": "silu",
|
15 |
"hidden_size": 8192,
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 28672,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 64,
|
|
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"high_freq_factor": 4.0,
|
29 |
+
"low_freq_factor": 1.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
"rope_theta": 500000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "bfloat16",
|
generation_config.json
CHANGED
@@ -3,9 +3,9 @@
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
|
|
6 |
128009
|
7 |
],
|
8 |
-
"max_length": 4096,
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
"transformers_version": "4.44.2"
|
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
6 |
+
128008,
|
7 |
128009
|
8 |
],
|
|
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
"transformers_version": "4.44.2"
|
model-00001-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4584507112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:977c2334588bbc60d0142bb23847038c0d4d7fbb00604a56ea25063f4c53266c
|
3 |
size 4584507112
|
model-00002-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cff4d7e8fb36e0a342db076a8c52d5bdbf10a283757d2bbdccedf886079f97ab
|
3 |
size 4664167376
|
model-00003-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf2c1f4036c0507a7af3317a46cfbc2add79189703378ea9496fd62ca1f9ed98
|
3 |
size 4999711704
|
model-00004-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966157032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8c79ccad2fd340042a03751a0e104631e33ea154b33a2743d9d073e626f3ef
|
3 |
size 4966157032
|
model-00005-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664134408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c49e7d28d9751b3188f01a4feb3ac782b2bebe0d4b240a1026592c18103d16e
|
3 |
size 4664134408
|
model-00006-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e648d03eebf2078023f0514d0e32541895a435bc5d850f99e50045f345a4570
|
3 |
size 4664167408
|
model-00007-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79ec85ad3bd1df9726741cf3f7ae3773cad90b746613c03f7ba730e0e52940c
|
3 |
size 4664167408
|
model-00008-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b8f88b8228935163f57952b251903172a4735e73d6aaf69f495c5423327364
|
3 |
size 4999711728
|
model-00009-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966157056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e830ec6dd2605935cc706a945ec75a42a4993dccb05d9b789af27fa2ff01cec9
|
3 |
size 4966157056
|
model-00010-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664134408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6591994087a9aed26db1aa113049b0a9d3de8e85b14f79fd1548ea1fcca3eca0
|
3 |
size 4664134408
|
model-00011-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f1f9d6170543610e1cc005e40c47deff8b670edf8e661bdf860762d7dc1dce9
|
3 |
size 4664167408
|
model-00012-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57184f3b4f70232df6ee596ee838ed39c9a1d357d55865975670a4a02a730de3
|
3 |
size 4664167408
|
model-00013-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2018ddde7951e0aa50b76974b69b81737b912bf5c4c989ae27152a108db00462
|
3 |
size 4999711728
|
model-00014-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966157056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50f3dae6b640d19cfae1e940d4d714b6ad45bb12c1d30ce9162d9e678703c7bc
|
3 |
size 4966157056
|
model-00015-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664134408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8f718485f9ac869dd3ca50770b403766eeb39f971d950f68dc59ea683a672f1
|
3 |
size 4664134408
|
model-00016-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82887fde6beda3167e36dd3cccf6ff956d190f6d924bc4081e0aae629f84b191
|
3 |
size 4664167408
|
model-00017-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d1950318d6a0d6371df574e8472bdbfc9049e0df77d8396eb254f12db8f1e7
|
3 |
size 4664167408
|
model-00018-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8af43c572238797042a17485b92a3348bbc65fa2b1c04c08058dcecae07440fd
|
3 |
size 4999711728
|
model-00019-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966157056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9b48401f232e309b6d26d8cad89958e594d3d76c34c371933e7c39b66b241a6
|
3 |
size 4966157056
|
model-00020-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664134408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca0d998ef02bfb8a7b85da43c50feb1173d5b47bae62b7b0442ed4b1d992a1a
|
3 |
size 4664134408
|
model-00021-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b2a89305e0b28cdcb3d1576ec2b06956f1a0efa957a514a9704e00a52da131
|
3 |
size 4664167408
|
model-00022-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8d493162f01edbe484ab8346c8033a194bdde7707f3857ed98a344d1318343f
|
3 |
size 4664167408
|
model-00023-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97977e60c31bdb045969d3b85b08605297c70fe6ebea9109ca38920db5afd98a
|
3 |
size 4999711728
|
model-00024-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966157056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a27b508b1b1bff7828e14d595725b9a63c4cd3ac0ef3611ce1a0178abb4c7e3d
|
3 |
size 4966157056
|
model-00025-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664134408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d3ff12d592edcfb2deeac20a6351fe0106f4b493a8c06ff0188d6146162ed60
|
3 |
size 4664134408
|
model-00026-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21ba906b003db4d39928e50b07f2809753b4228012271938ec904dfffc61998b
|
3 |
size 4664167408
|
model-00027-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664167408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77cfb639de7d7f194e6ed5688dd42958aa7a57d4e614f65a7fe5024638712415
|
3 |
size 4664167408
|
model-00028-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999711728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e8b4b8ddbf31e4357be1b316e275513ab4936d712ac97ce084e6183e0491ce
|
3 |
size 4999711728
|
model-00029-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4966173536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0be1a3ced841340a41c2547c68bdc9ee74180951308b028ad66dbd68a8cbfe22
|
3 |
size 4966173536
|
model-00030-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2101444736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ac323f1e5a25c129a545499147d732895f3130b28f13c7c51fac22c82897c63
|
3 |
size 2101444736
|