TweedBeetle
commited on
Commit
•
7b78f63
1
Parent(s):
c896581
Upload LlamaForCausalLM
Browse files- config.json +4 -6
- generation_config.json +4 -5
- model-00001-of-00009.safetensors +1 -1
- model-00002-of-00009.safetensors +1 -1
- model-00003-of-00009.safetensors +1 -1
- model-00004-of-00009.safetensors +1 -1
- model-00005-of-00009.safetensors +1 -1
- model-00006-of-00009.safetensors +1 -1
- model-00007-of-00009.safetensors +1 -1
- model-00008-of-00009.safetensors +1 -1
- model-00009-of-00009.safetensors +1 -1
config.json
CHANGED
@@ -1,16 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
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": 4096,
|
16 |
"initializer_range": 0.02,
|
@@ -21,6 +17,7 @@
|
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 32,
|
23 |
"num_key_value_heads": 8,
|
|
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": {
|
@@ -34,6 +31,7 @@
|
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "bfloat16",
|
36 |
"transformers_version": "4.44.2",
|
|
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 128256
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/Meta-Llama-3.1-8B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 128004,
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": {
|
|
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
"transformers_version": "4.44.2",
|
34 |
+
"unsloth_version": "2024.9",
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128256
|
37 |
}
|
generation_config.json
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 128000,
|
3 |
"do_sample": true,
|
4 |
-
"eos_token_id":
|
5 |
-
|
6 |
-
|
7 |
-
128009
|
8 |
-
],
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
"transformers_version": "4.44.2"
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
"do_sample": true,
|
5 |
+
"eos_token_id": 128001,
|
6 |
+
"max_length": 131072,
|
7 |
+
"pad_token_id": 128004,
|
|
|
|
|
8 |
"temperature": 0.6,
|
9 |
"top_p": 0.9,
|
10 |
"transformers_version": "4.44.2"
|
model-00001-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1973455376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3382d369f0fc32241db9f9d8946e759bc6371520c41911e2702ea1002164fcc
|
3 |
size 1973455376
|
model-00002-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1895895336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e650ddf6e526f8bd34e75b8c521124f2d518c1ae2e718e21cb101f996cdb60a
|
3 |
size 1895895336
|
model-00003-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1979798040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34c617c6a30e77483c8a96e97c64066b9d1c3a123a62bd25f7787570c1958175
|
3 |
size 1979798040
|
model-00004-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1946227368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c0a55d047411e7fa1ee45e2ae3fa191ed6e03b204d05204e8ca62392cd1a78
|
3 |
size 1946227368
|
model-00005-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1979798064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d49922a359a42cbdc29f52ddd70e1205ed323516d8499d420de54e7115eb8dd
|
3 |
size 1979798064
|
model-00006-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1946227368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba861cc7676340cd8702a91896629507041f0e61f23fa25faa13fa79807b8571
|
3 |
size 1946227368
|
model-00007-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1979798064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27fb7ece4c2e0cf7aab5dccf1ac19067b86fc7bf9a6d6ddc72fef0aca6368386
|
3 |
size 1979798064
|
model-00008-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1308683424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd6a66e2a58a822df5899ac1ac390b9984f86a63cb25f6c807459d291b715e8
|
3 |
size 1308683424
|
model-00009-of-00009.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1050673280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6feef628d893df7809d975f4c3a109a655e5e4126ac4ee28e8e0464504c86b12
|
3 |
size 1050673280
|