surya-narayanan
commited on
Commit
•
fb62632
1
Parent(s):
1f9994b
Training in progress, epoch 1
Browse files- adapter_config.json +36 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "MistralForCausalLM",
|
5 |
+
"parent_library": "transformers.models.mistral.modeling_mistral"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 256,
|
17 |
+
"lora_dropout": 0.1,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": [
|
21 |
+
"ln_f"
|
22 |
+
],
|
23 |
+
"peft_type": "LORA",
|
24 |
+
"r": 256,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"v_proj",
|
29 |
+
"k_proj",
|
30 |
+
"o_proj",
|
31 |
+
"q_proj"
|
32 |
+
],
|
33 |
+
"task_type": null,
|
34 |
+
"use_dora": false,
|
35 |
+
"use_rslora": false
|
36 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f18521cf8a4056dbe3dda552a77d506c9542574e6ed4ac6adaae40f447d56444
|
3 |
+
size 872450448
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6583250c9693827282f8176e316b707698ccbaaadab1687bcf16539eaf333438
|
3 |
+
size 4984
|