sometimesanotion
commited on
Commit
•
1b3d3f3
1
Parent(s):
5e533c7
Upload 3 files
Browse files
CultriX/Qwen2.5-14B-Wernicke/Qwen/Qwen2.5-14B-Instruct-rank128/README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-14B-Instruct
|
4 |
+
- CultriX/Qwen2.5-14B-Wernicke
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- peft
|
9 |
+
|
10 |
+
---
|
11 |
+
# Untitled LoRA Model (1)
|
12 |
+
|
13 |
+
This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
|
14 |
+
|
15 |
+
## LoRA Details
|
16 |
+
|
17 |
+
This LoRA adapter was extracted from [CultriX/Qwen2.5-14B-Wernicke](https://huggingface.co/CultriX/Qwen2.5-14B-Wernicke) and uses [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) as a base.
|
18 |
+
|
19 |
+
### Parameters
|
20 |
+
|
21 |
+
The following command was used to extract this LoRA adapter:
|
22 |
+
|
23 |
+
```sh
|
24 |
+
mergekit-extract-lora CultriX/Qwen2.5-14B-Wernicke Qwen/Qwen2.5-14B-Instruct OUTPUT_PATH --rank=128
|
25 |
+
```
|
CultriX/Qwen2.5-14B-Wernicke/Qwen/Qwen2.5-14B-Instruct-rank128/adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 128,
|
13 |
+
"lora_dropout": 0,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": [
|
17 |
+
"post_attention_layernorm",
|
18 |
+
"norm",
|
19 |
+
"input_layernorm"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"down_proj",
|
27 |
+
"k_proj",
|
28 |
+
"up_proj",
|
29 |
+
"q_proj",
|
30 |
+
"lm_head",
|
31 |
+
"v_proj",
|
32 |
+
"o_proj",
|
33 |
+
"gate_proj",
|
34 |
+
"embed_tokens"
|
35 |
+
],
|
36 |
+
"task_type": "CAUSAL_LM",
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
CultriX/Qwen2.5-14B-Wernicke/Qwen/Qwen2.5-14B-Instruct-rank128/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7ba3c00668ed49de07773389eddda66e1a857999d0220dc32e25c87035e9fb4
|
3 |
+
size 1182582064
|