Upload LlamaForCausalLM
Browse files- config.json +34 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/user/finetuning-subnet/local-models/training/2024-05-17_14-17-33",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 100289,
|
9 |
+
"eos_token_id": 100290,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5632,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"num_key_value_heads": 32,
|
21 |
+
"partial_rotary_factor": 0.25,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"qk_layernorm": false,
|
24 |
+
"rms_norm_eps": 1e-06,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 10000,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.40.0",
|
30 |
+
"use_cache": true,
|
31 |
+
"use_parallel_residual": false,
|
32 |
+
"use_qkv_bias": true,
|
33 |
+
"vocab_size": 100352
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100289,
|
4 |
+
"eos_token_id": 100290,
|
5 |
+
"transformers_version": "4.40.0"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0844a0a50cf535ebda9c53c1c8c895a1a2e81056e5a890759dad1d1bcf7235b4
|
3 |
+
size 3288560400
|