NowaBwagel0
commited on
Commit
•
c15d0e2
1
Parent(s):
53b4e8b
Training in progress, step 264
Browse files
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "JackFram/llama-68m",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 2,
|
19 |
+
"num_key_value_heads": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.42.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bf56ee83260fde89e0fb0c75299781b01ec56374207a45a3529203f18d66bb8
|
3 |
+
size 272123144
|
runs/May24_17-55-02_afc171c95cab/events.out.tfevents.1716573303.afc171c95cab.17338.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fedbd28bffc42e0c44b8e3049386ba2a3bf5dc338edb703eae6569988544e9b
|
3 |
+
size 19058
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1892436d6f67cbf260858c1d8b64dea09b34f940aa4c979ac7e1908fd78aff5f
|
3 |
+
size 5112
|