Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,11 @@ tags:
|
|
| 7 |
- unsloth
|
| 8 |
- sft
|
| 9 |
licence: license
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for Qwen3-0.6B-Alpaca
|
|
@@ -17,12 +22,34 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
| 17 |
## Quick start
|
| 18 |
|
| 19 |
```python
|
| 20 |
-
from transformers import
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
```
|
| 27 |
|
| 28 |
## Training procedure
|
|
|
|
| 7 |
- unsloth
|
| 8 |
- sft
|
| 9 |
licence: license
|
| 10 |
+
datasets:
|
| 11 |
+
- RaagulQB/alpaca_coding_dataset_full
|
| 12 |
+
- tatsu-lab/alpaca
|
| 13 |
+
base_model:
|
| 14 |
+
- Qwen/Qwen3-0.6B-Base
|
| 15 |
---
|
| 16 |
|
| 17 |
# Model Card for Qwen3-0.6B-Alpaca
|
|
|
|
| 22 |
## Quick start
|
| 23 |
|
| 24 |
```python
|
| 25 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 26 |
|
| 27 |
+
model_name='wesjos/Qwen3-0.6B-Alpaca'
|
| 28 |
+
|
| 29 |
+
model=AutoModelForCausalLM.from_pretrained(model_name)
|
| 30 |
+
tokenizer=AutoTokenizer.from_pretrained(model_name)
|
| 31 |
+
|
| 32 |
+
alpaca_prompt = """"Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
| 33 |
+
|
| 34 |
+
### Instruction:
|
| 35 |
+
{}
|
| 36 |
+
|
| 37 |
+
### Input:
|
| 38 |
+
{}
|
| 39 |
+
|
| 40 |
+
### Response:
|
| 41 |
+
"""
|
| 42 |
+
|
| 43 |
+
inputs = tokenizer(
|
| 44 |
+
[
|
| 45 |
+
alpaca_prompt.format(
|
| 46 |
+
"完成以下代码要求", # instruction
|
| 47 |
+
"使用python写一个transformer神经网络" #Input
|
| 48 |
+
)
|
| 49 |
+
], return_tensors = "pt").to("cuda")
|
| 50 |
+
|
| 51 |
+
outputs = model.generate(**inputs, max_new_tokens=1024, use_cache=True,temperature=0.6,do_sample=True,top_p=0.95,top_k=20)
|
| 52 |
+
print(tokenizer.batch_decode(outputs)[0])
|
| 53 |
```
|
| 54 |
|
| 55 |
## Training procedure
|