zhaozitian
commited on
Commit
•
aa15794
1
Parent(s):
a9b1c69
Update README.md
Browse files
README.md
CHANGED
@@ -1,22 +1,26 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
-
## Training procedure
|
5 |
|
|
|
6 |
|
7 |
-
|
8 |
-
- load_in_8bit: True
|
9 |
-
- llm_int8_threshold: 6.0
|
10 |
-
- llm_int8_skip_modules: None
|
11 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
|
13 |
-
|
14 |
-
-
|
15 |
-
-
|
16 |
-
-
|
17 |
-
-
|
18 |
-
|
|
|
|
|
|
|
19 |
|
20 |
-
-
|
21 |
|
22 |
-
|
|
|
1 |
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
datasets:
|
4 |
+
- c-s-ale/alpaca-gpt4-data-zh
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- zh
|
8 |
---
|
|
|
9 |
|
10 |
+
This model is an LoRA adapter file from finetuned Llama-2-13b-chat-hf model. This is an experimental model.
|
11 |
|
12 |
+
This model is presented by IceBear-AI.
|
|
|
|
|
|
|
|
|
13 |
|
14 |
+
To run it, you need to:
|
15 |
+
- Agree with Meta's agreements to download the Llama-2-13b-chat-hf model from here: https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
|
16 |
+
- Clone this repository
|
17 |
+
- Clone the Alpaca-LoRA repository from here: https://github.com/tloen/alpaca-lora
|
18 |
+
- Use this command to run it:
|
19 |
+
-python generate.py \
|
20 |
+
--load_8bit \
|
21 |
+
--base_model 'PATH_TO_YOUR_LOCAL_LLAMA_2_13B_CHAT_HF' \
|
22 |
+
--lora_weights 'PATH_TO_YOUR_LOCAL_FILE_OF_THIS_MODEL'
|
23 |
|
24 |
+
You must agree with Meta/Llama-2's agreements to use this model.
|
25 |
|
26 |
+
If you would like to contact us, please don't hesitate to email to icebearai@163.com.
|