Upload LlamaForCausalLM
Browse files- config.json +5 -15
- generation_config.json +3 -3
- model-00001-of-00030.safetensors +2 -2
- 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 +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
@@ -1,21 +1,17 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "mattshumer/Reflection-70B",
|
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":
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 64,
|
@@ -23,17 +19,11 @@
|
|
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",
|
36 |
"transformers_version": "4.44.2",
|
37 |
"use_cache": true,
|
38 |
-
"vocab_size":
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mattshumer/Reflection-Llama-3.1-70B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 8192,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 64,
|
|
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.44.2",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 128262
|
29 |
}
|
generation_config.json
CHANGED
@@ -3,10 +3,10 @@
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
128001,
|
6 |
-
128008,
|
7 |
128009
|
8 |
],
|
9 |
-
"
|
10 |
-
"
|
|
|
11 |
"transformers_version": "4.44.2"
|
12 |
}
|
|
|
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"
|
12 |
}
|
model-00001-of-00030.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:644f054373639c20fba9270749c25b9e91ecaf538fd3ddd48268578ea920c4ef
|
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:a1222b2ef9549c6fd5d104ed973df737c06c17fc9c7592336fdd6e048605ed25
|
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 sha256:86191b3774de93e70b405ab5f485bcd9adbf73d47043e747cc823b27d419db31
|
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 sha256:6253872ad9d98cbc79110974734a719240e3d4a2c2fc914d1a319d679a377e43
|
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 sha256:023d5918deb9095bfb2c4d0bd316f2db0abecd4509ddce643fa9526638ea646d
|
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 sha256:798b92d3c8b878af625420583f746f7055e444e8daca99496303497ec54ec3da
|
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 sha256:8293f5521baf1f314d63104bf821e52c9aad1a1d9eb9987e3d8bd39fe6e903f7
|
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 sha256:454249979a0b1c25a0eb72b5ac5222da0a9b11eab459d207aaa189afaf6e01b3
|
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:e54f6ac1e9ad1843b756445e8bc41790a72a0731d6d05871ae3e7bd5fb804cd6
|
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 sha256:06628e1b8b130140ecfd154db7a2b16189d7616870d7fc63b5ae760286b798c2
|
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:c726cfc07ba932d8f31eb91f749385c87aaccb8d6a8fb05f39b67d619d3a8d21
|
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:e3e601196392560b3ac31fa1f839c472e852872ec3b23e8fff5427dd6360c81f
|
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:ad8782aa3ab097eba3f8233efce781d8d0cabb45f26d56a917c7dcb097a332af
|
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:b012d4e9a88fdfd7856cc8af28af2971ec325693b3e18457ad899257cec8610c
|
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:c8c63e46229d67c88e9e2b9ad4497f779fe922b3c21d79ff7c04d04e5786df37
|
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 sha256:46e76a2cd2b2aaa7524b1187db6e7d2aa7c873e2dd3c2ce89c022e061acace37
|
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:a6b39ca86411851783a21aca3e109c276bae894359b6e4021d4c26a73f291a9c
|
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:e17f135838f01e5d1d45970cef560d258b5fe1b3f87c5c5574d6c1ae02c2a07f
|
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:a6124d9e0abfdfcd3b98250288c430fb394e6b129c8edac63e25c1e5b1d0aa30
|
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:e0092e30f1301d56465c8071274a1df95bc5c48edcda088282fc4e91ddef3b6d
|
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:a8d42721d3ac63fff254f875048733de3aa2b80fad2e8581c76cc939245a59e6
|
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:c23771b5cddf9dff11f23ee7e76dafc2b7f3215ff0f5baf3ec69a5a85a2b5eb5
|
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:ceba963387003ba076d69cf86b0b0135ee80de64087a6029060c56435ebf0644
|
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 sha256:68644ff8c2e5dbffe0b70334ee575f70919db332f53e6e08c7ffcb930655c4c7
|
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:f75fe67d2db6f5568bb83d295ba515ab83010cf94a98da2feeea32f13afa6923
|
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 sha256:7637913f3caa0aa2cd1a0cc736deb5640e872ae174c87d7c6b5ccdde2d2bc521
|
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:b239e31cf5c45ba683183ea5008030ddcd2580b151870bb928780a03158312e3
|
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 sha256:1e6c5da91457037e4cb0a473b59d61ceb07ca0205fd98d7dd187b711d231b98f
|
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 sha256:18673cfa947ea640738188442beb37dadb25525c0d7a950ff45b6e633ce7329d
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4999d998507a81d54650a71bd15cb4fbb42d6eb7ada1e1a3fec4eedbefcca93f
|
3 |
+
size 2101444736
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00030-of-00030.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 141107609600
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00030-of-00030.safetensors",
|