mariatager
commited on
Commit
•
0eb2042
1
Parent(s):
4d6ec96
finetuned model
Browse files- config.json +63 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_remove_final_layer_norm": false,
|
3 |
+
"activation_function": "relu",
|
4 |
+
"alpha_pattern": {},
|
5 |
+
"architectures": [
|
6 |
+
"OPTForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auto_mapping": {
|
10 |
+
"base_model_class": "OPTForCausalLM",
|
11 |
+
"parent_library": "transformers.models.opt.modeling_opt"
|
12 |
+
},
|
13 |
+
"base_model_name_or_path": "facebook/galactica-125m",
|
14 |
+
"bias": "none",
|
15 |
+
"bos_token_id": 2,
|
16 |
+
"do_layer_norm_before": true,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"enable_bias": true,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"fan_in_fan_out": false,
|
21 |
+
"ffn_dim": 3072,
|
22 |
+
"hidden_size": 768,
|
23 |
+
"inference_mode": true,
|
24 |
+
"init_lora_weights": true,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"layer_norm_elementwise_affine": true,
|
27 |
+
"layer_replication": null,
|
28 |
+
"layerdrop": 0.0,
|
29 |
+
"layers_pattern": null,
|
30 |
+
"layers_to_transform": null,
|
31 |
+
"loftq_config": {},
|
32 |
+
"lora_alpha": 16,
|
33 |
+
"lora_dropout": 0,
|
34 |
+
"max_position_embeddings": 2048,
|
35 |
+
"megatron_config": null,
|
36 |
+
"megatron_core": "megatron.core",
|
37 |
+
"model_type": "opt",
|
38 |
+
"modules_to_save": null,
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"pad_token_id": 1,
|
42 |
+
"peft_type": "LORA",
|
43 |
+
"r": 16,
|
44 |
+
"rank_pattern": {},
|
45 |
+
"revision": null,
|
46 |
+
"target_modules": [
|
47 |
+
"k_proj",
|
48 |
+
"v_proj",
|
49 |
+
"down_proj",
|
50 |
+
"q_proj",
|
51 |
+
"o_proj",
|
52 |
+
"gate_proj",
|
53 |
+
"up_proj"
|
54 |
+
],
|
55 |
+
"task_type": null,
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.41.2",
|
58 |
+
"use_cache": true,
|
59 |
+
"use_dora": false,
|
60 |
+
"use_rslora": false,
|
61 |
+
"vocab_size": 50272,
|
62 |
+
"word_embed_proj_dim": 768
|
63 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b900be04270fec8ffa4721eee8623431249fa052642752e5c60150e06e7db15a
|
3 |
+
size 500979600
|