Syed-Hasan-8503
commited on
Commit
•
ec1fedf
1
Parent(s):
3c05b52
Upload folder using huggingface_hub
Browse files- config.json +30 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nisten/Biggie-SmoLlm-0.15B-Base",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 576,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 9,
|
18 |
+
"num_hidden_layers": 35,
|
19 |
+
"num_key_value_heads": 3,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": true,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.44.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 49152
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.44.0"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b0c2864032ae69d61ad353312ba1091f08f68a4816d0ecce5d0766b46cdcdcd
|
3 |
+
size 304466592
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62cb91b9077cc372d33e151d35147a3918213930f370f800a0078308790cb625
|
3 |
+
size 609128762
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36eb3c91b3077080e254ba8fd9a96b4afe9cf22aec04441fdc41ff8bc2a91d56
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1df5b6d4010d6e21aa16c9e21e8105b249418b2b763efb6941307015be822629
|
3 |
+
size 1000
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:180316c376d31e9ea91140115fc668ee9a43433af90dee8d9e0d436f94e88939
|
3 |
+
size 5240
|