Spaces:
Build error
Build error
Upload folder using huggingface_hub
Browse files- README.md +40 -7
- app.py +88 -0
- requirements.txt +7 -0
README.md
CHANGED
|
@@ -1,12 +1,45 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
app_file: app.py
|
| 9 |
-
pinned:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: code-il-E4B
|
| 3 |
+
emoji: 馃捇
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 4.44.0
|
| 8 |
app_file: app.py
|
| 9 |
+
pinned: true
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
short_description: Israeli code model 4B - Gemma 4 + NVIDIA OpenCodeInstruct
|
| 12 |
+
models:
|
| 13 |
+
- BrainboxAI/code-il-E4B-safetensors
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# code-il-E4B
|
| 17 |
+
|
| 18 |
+
诪讜讚诇 拽讜讚 讬砖专讗诇讬 讘讙讜讚诇 4 诪讬诇讬讗专讚 驻专诪讟专讬诐. 专抓 注诇 诪讞砖讘 谞讬讬讚, 转讜诪讱 讘注讘专讬转, 诪转诪讞讛 讘-Python 讜-TypeScript.
|
| 19 |
+
|
| 20 |
+
## 诪讛 诪讬讜讞讚 讘讜
|
| 21 |
+
|
| 22 |
+
- **讘住讬住**: Gemma 4 E4B 砖诇 Google
|
| 23 |
+
- **fine-tuning**: 注诇 dataset 砖诇 5 诪讬诇讬讜谉 讚讜讙诪讗讜转 拽讜讚 诪-NVIDIA + 40K 讚讜讙诪讗讜转 注讘专讬讜转 砖讗住驻转讬
|
| 24 |
+
- **专抓 on-device**: 4B 驻专诪讟专讬诐 谞讻谞住讬诐 讘讝讬讻专讜谉 砖诇 诪讞砖讘 谞讬讬讚 专讙讬诇
|
| 25 |
+
- **讚讜-诇砖讜谞讬**: 转讜诪讱 讘拽讜讚 讘讗谞讙诇讬转 讜讛住讘专讬诐 讘注讘专讬转
|
| 26 |
+
|
| 27 |
+
## 讗讬讱 诪专讬爪讬诐 诪拽讜诪讬转
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 31 |
+
|
| 32 |
+
tokenizer = AutoTokenizer.from_pretrained("BrainboxAI/code-il-E4B-safetensors")
|
| 33 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 34 |
+
"BrainboxAI/code-il-E4B-safetensors",
|
| 35 |
+
torch_dtype="auto",
|
| 36 |
+
device_map="auto",
|
| 37 |
+
)
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
## 谞讘谞讛 注诇 讬讚讬
|
| 41 |
+
|
| 42 |
+
[BrainboxAI](https://huggingface.co/BrainboxAI) - 讞讘专转 AI 讬砖专讗诇讬转 砖讘讜谞讛 诪讜讚诇讬诐 讬砖专讗诇讬讬诐 诇转注砖讬讬讛.
|
| 43 |
+
诪讜讚诇讬诐 谞讜住驻讬诐: [law-il-E2B](https://huggingface.co/BrainboxAI/law-il-E2B) (诪砖驻讟讬), [med-il-E4B](https://huggingface.co/BrainboxAI/med-il-E4B) (专驻讜讗讬).
|
| 44 |
+
|
| 45 |
+
Built with [Unsloth](https://unsloth.ai) for 2x faster training.
|
app.py
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import spaces
|
| 3 |
+
import torch
|
| 4 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
|
| 5 |
+
from threading import Thread
|
| 6 |
+
|
| 7 |
+
MODEL_ID = "BrainboxAI/code-il-E4B-safetensors"
|
| 8 |
+
|
| 9 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
|
| 10 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 11 |
+
MODEL_ID,
|
| 12 |
+
torch_dtype=torch.bfloat16,
|
| 13 |
+
device_map="auto",
|
| 14 |
+
)
|
| 15 |
+
|
| 16 |
+
EXAMPLES = [
|
| 17 |
+
["Implement binary search in TypeScript with full edge case handling and JSDoc comments."],
|
| 18 |
+
["Build a FastAPI endpoint that accepts a file upload, validates it's a PDF under 10MB, and returns its text content."],
|
| 19 |
+
["Write an n8n Code node (JavaScript) that takes input items, deduplicates by 'email' field, and returns the unique ones."],
|
| 20 |
+
["讛住讘专 讗转 讛拽讜讚 讛讘讗 讜转爪讬注 砖讬驻讜专讬诐:\n\nfunction calc(arr) {\n let s = 0;\n for (let i = 0; i < arr.length; i++) s += arr[i];\n return s / arr.length;\n}"],
|
| 21 |
+
]
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
@spaces.GPU(duration=60)
|
| 25 |
+
def generate(message, history, temperature, max_tokens):
|
| 26 |
+
messages = []
|
| 27 |
+
for user_msg, assistant_msg in history:
|
| 28 |
+
messages.append({"role": "user", "content": user_msg})
|
| 29 |
+
if assistant_msg:
|
| 30 |
+
messages.append({"role": "assistant", "content": assistant_msg})
|
| 31 |
+
messages.append({"role": "user", "content": message})
|
| 32 |
+
|
| 33 |
+
inputs = tokenizer.apply_chat_template(
|
| 34 |
+
messages,
|
| 35 |
+
return_tensors="pt",
|
| 36 |
+
add_generation_prompt=True,
|
| 37 |
+
).to(model.device)
|
| 38 |
+
|
| 39 |
+
streamer = TextIteratorStreamer(
|
| 40 |
+
tokenizer, skip_prompt=True, skip_special_tokens=True
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
thread = Thread(target=model.generate, kwargs={
|
| 44 |
+
"input_ids": inputs,
|
| 45 |
+
"max_new_tokens": max_tokens,
|
| 46 |
+
"temperature": temperature,
|
| 47 |
+
"top_p": 0.95,
|
| 48 |
+
"do_sample": temperature > 0,
|
| 49 |
+
"streamer": streamer,
|
| 50 |
+
})
|
| 51 |
+
thread.start()
|
| 52 |
+
|
| 53 |
+
output = ""
|
| 54 |
+
for token in streamer:
|
| 55 |
+
output += token
|
| 56 |
+
yield output
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), title="Code-IL E4B") as demo:
|
| 60 |
+
gr.Markdown("""
|
| 61 |
+
# code-il-E4B
|
| 62 |
+
### 诪讜讚诇 拽讜讚 讬砖专讗诇讬 - 4 诪讬诇讬讗专讚 驻专诪讟专讬诐, 专抓 注诇 诪讞砖讘 谞讬讬讚
|
| 63 |
+
|
| 64 |
+
诪讜讚诇 诪讘讜住住 Gemma 4 E4B 砖讗讜诪谉 注诇 OpenCodeInstruct 砖诇 NVIDIA + dataset 拽讜讚 注讘专讬-讗谞讙诇讬 诪砖诇讬.
|
| 65 |
+
诪转诪讞讛 讘-Python, TypeScript, n8n, 讜转讜诪讱 讘注讘专讬转.
|
| 66 |
+
|
| 67 |
+
**By [BrainboxAI](https://huggingface.co/BrainboxAI)** - Powered by Unsloth
|
| 68 |
+
""")
|
| 69 |
+
|
| 70 |
+
chat = gr.ChatInterface(
|
| 71 |
+
fn=generate,
|
| 72 |
+
examples=EXAMPLES,
|
| 73 |
+
cache_examples=False,
|
| 74 |
+
additional_inputs=[
|
| 75 |
+
gr.Slider(0.0, 1.0, value=0.2, step=0.05, label="Temperature"),
|
| 76 |
+
gr.Slider(128, 2048, value=1024, step=128, label="Max Tokens"),
|
| 77 |
+
],
|
| 78 |
+
additional_inputs_accordion=gr.Accordion("鈿欙笍 讛讙讚专讜转 诪转拽讚诪讜转", open=False),
|
| 79 |
+
)
|
| 80 |
+
|
| 81 |
+
gr.Markdown("""
|
| 82 |
+
---
|
| 83 |
+
**Training**: NVIDIA OpenCodeInstruct (4.97M) + BrainboxAI/code-training-il (40k) + bleugreen/typescript-instruct (41k)
|
| 84 |
+
**Format**: Safetensors 16-bit | **License**: Apache 2.0 | **Languages**: English + 注讘专讬转
|
| 85 |
+
""")
|
| 86 |
+
|
| 87 |
+
if __name__ == "__main__":
|
| 88 |
+
demo.queue().launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch
|
| 2 |
+
transformers>=4.45.0
|
| 3 |
+
accelerate
|
| 4 |
+
spaces
|
| 5 |
+
gradio>=4.44.0
|
| 6 |
+
sentencepiece
|
| 7 |
+
protobuf
|