Text Generation
Transformers
Safetensors
llama
code
conversational
text-generation-inference
4-bit precision
awq
Instructions to use TechxGenus/CursorCore-DS-1.3B-SR-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TechxGenus/CursorCore-DS-1.3B-SR-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TechxGenus/CursorCore-DS-1.3B-SR-AWQ") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TechxGenus/CursorCore-DS-1.3B-SR-AWQ") model = AutoModelForCausalLM.from_pretrained("TechxGenus/CursorCore-DS-1.3B-SR-AWQ") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TechxGenus/CursorCore-DS-1.3B-SR-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TechxGenus/CursorCore-DS-1.3B-SR-AWQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TechxGenus/CursorCore-DS-1.3B-SR-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/TechxGenus/CursorCore-DS-1.3B-SR-AWQ
- SGLang
How to use TechxGenus/CursorCore-DS-1.3B-SR-AWQ with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "TechxGenus/CursorCore-DS-1.3B-SR-AWQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TechxGenus/CursorCore-DS-1.3B-SR-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "TechxGenus/CursorCore-DS-1.3B-SR-AWQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TechxGenus/CursorCore-DS-1.3B-SR-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use TechxGenus/CursorCore-DS-1.3B-SR-AWQ with Docker Model Runner:
docker model run hf.co/TechxGenus/CursorCore-DS-1.3B-SR-AWQ
Link to paper page
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,20 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
tags:
|
| 3 |
-
- code
|
| 4 |
base_model:
|
| 5 |
- TechxGenus/CursorCore-DS-1.3B-SR
|
| 6 |
library_name: transformers
|
| 7 |
-
pipeline_tag: text-generation
|
| 8 |
license: other
|
| 9 |
license_name: deepseek
|
| 10 |
license_link: LICENSE
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# CursorCore: Assist Programming through Aligning Anything
|
| 14 |
|
| 15 |
<p align="center">
|
| 16 |
<a href="http://arxiv.org/abs/2410.07002">[📄arXiv]</a> |
|
| 17 |
-
<a href="https://
|
| 18 |
<a href="https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2">[🤖Models]</a> |
|
| 19 |
<a href="https://github.com/TechxGenus/CursorCore">[🛠️Code]</a> |
|
| 20 |
<a href="https://github.com/TechxGenus/CursorWeb">[Web]</a> |
|
|
@@ -44,7 +44,7 @@ CursorCore is a series of open-source models designed for AI-assisted programmin
|
|
| 44 |
<img width="100%" alt="conversation" src="https://raw.githubusercontent.com/TechxGenus/CursorCore/main/pictures/conversation.png">
|
| 45 |
</p>
|
| 46 |
|
| 47 |
-

|
| 48 |
|
| 49 |
## Models
|
| 50 |
|
|
@@ -116,13 +116,27 @@ sample = {
|
|
| 116 |
{
|
| 117 |
"type": "code",
|
| 118 |
"lang": "python",
|
| 119 |
-
"code": """def quick_sort(arr):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
}
|
| 121 |
],
|
| 122 |
"current": {
|
| 123 |
"type": "code",
|
| 124 |
"lang": "python",
|
| 125 |
-
"code": """def quick_sort(array):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
},
|
| 127 |
"user": ""
|
| 128 |
}
|
|
@@ -204,7 +218,14 @@ sample = {
|
|
| 204 |
"current": {
|
| 205 |
"type": "code",
|
| 206 |
"lang": "python",
|
| 207 |
-
"code": """def quick_sort(array):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
},
|
| 209 |
"user": "Add Docstring."
|
| 210 |
}
|
|
@@ -275,7 +296,14 @@ sample = {
|
|
| 275 |
"current": {
|
| 276 |
"type": "code",
|
| 277 |
"lang": "python",
|
| 278 |
-
"code": """def quick_sort(array):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 279 |
},
|
| 280 |
"user": "Add Docstring."
|
| 281 |
}
|
|
@@ -344,7 +372,14 @@ sample = {
|
|
| 344 |
"current": {
|
| 345 |
"type": "code",
|
| 346 |
"lang": "python",
|
| 347 |
-
"code": """def quick_sort(array):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 348 |
},
|
| 349 |
"user": "Add Docstring."
|
| 350 |
}
|
|
@@ -416,4 +451,4 @@ CursorCore is still in a very early stage, and lots of work is needed to achieve
|
|
| 416 |
|
| 417 |
## Contribution
|
| 418 |
|
| 419 |
-
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- TechxGenus/CursorCore-DS-1.3B-SR
|
| 4 |
library_name: transformers
|
|
|
|
| 5 |
license: other
|
| 6 |
license_name: deepseek
|
| 7 |
license_link: LICENSE
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
tags:
|
| 10 |
+
- code
|
| 11 |
---
|
| 12 |
|
| 13 |
# CursorCore: Assist Programming through Aligning Anything
|
| 14 |
|
| 15 |
<p align="center">
|
| 16 |
<a href="http://arxiv.org/abs/2410.07002">[📄arXiv]</a> |
|
| 17 |
+
<a href="https://huggingface.co/papers/2410.07002">[🤗HF Paper]</a> |
|
| 18 |
<a href="https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2">[🤖Models]</a> |
|
| 19 |
<a href="https://github.com/TechxGenus/CursorCore">[🛠️Code]</a> |
|
| 20 |
<a href="https://github.com/TechxGenus/CursorWeb">[Web]</a> |
|
|
|
|
| 44 |
<img width="100%" alt="conversation" src="https://raw.githubusercontent.com/TechxGenus/CursorCore/main/pictures/conversation.png">
|
| 45 |
</p>
|
| 46 |
|
| 47 |
+

|
| 48 |
|
| 49 |
## Models
|
| 50 |
|
|
|
|
| 116 |
{
|
| 117 |
"type": "code",
|
| 118 |
"lang": "python",
|
| 119 |
+
"code": """def quick_sort(arr):
|
| 120 |
+
if len(arr) <= 1:
|
| 121 |
+
return arr
|
| 122 |
+
pivot = arr[len(arr) // 2]
|
| 123 |
+
left = [x for x in arr if x < pivot]
|
| 124 |
+
middle = [x for x in arr if x == pivot]
|
| 125 |
+
right = [x for x in arr if x > pivot]
|
| 126 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
| 127 |
}
|
| 128 |
],
|
| 129 |
"current": {
|
| 130 |
"type": "code",
|
| 131 |
"lang": "python",
|
| 132 |
+
"code": """def quick_sort(array):
|
| 133 |
+
if len(arr) <= 1:
|
| 134 |
+
return arr
|
| 135 |
+
pivot = arr[len(arr) // 2]
|
| 136 |
+
left = [x for x in arr if x < pivot]
|
| 137 |
+
middle = [x for x in arr if x == pivot]
|
| 138 |
+
right = [x for x in arr if x > pivot]
|
| 139 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
| 140 |
},
|
| 141 |
"user": ""
|
| 142 |
}
|
|
|
|
| 218 |
"current": {
|
| 219 |
"type": "code",
|
| 220 |
"lang": "python",
|
| 221 |
+
"code": """def quick_sort(array):
|
| 222 |
+
if len(arr) <= 1:
|
| 223 |
+
return arr
|
| 224 |
+
pivot = arr[len(arr) // 2]
|
| 225 |
+
left = [x for x in arr if x < pivot]
|
| 226 |
+
middle = [x for x in arr if x == pivot]
|
| 227 |
+
right = [x for x in arr if x > pivot]
|
| 228 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
| 229 |
},
|
| 230 |
"user": "Add Docstring."
|
| 231 |
}
|
|
|
|
| 296 |
"current": {
|
| 297 |
"type": "code",
|
| 298 |
"lang": "python",
|
| 299 |
+
"code": """def quick_sort(array):
|
| 300 |
+
if len(arr) <= 1:
|
| 301 |
+
return arr
|
| 302 |
+
pivot = arr[len(arr) // 2]
|
| 303 |
+
left = [x for x in arr if x < pivot]
|
| 304 |
+
middle = [x for x in arr if x == pivot]
|
| 305 |
+
right = [x for x in arr if x > pivot]
|
| 306 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
| 307 |
},
|
| 308 |
"user": "Add Docstring."
|
| 309 |
}
|
|
|
|
| 372 |
"current": {
|
| 373 |
"type": "code",
|
| 374 |
"lang": "python",
|
| 375 |
+
"code": """def quick_sort(array):
|
| 376 |
+
if len(arr) <= 1:
|
| 377 |
+
return arr
|
| 378 |
+
pivot = arr[len(arr) // 2]
|
| 379 |
+
left = [x for x in arr if x < pivot]
|
| 380 |
+
middle = [x for x in arr if x == pivot]
|
| 381 |
+
right = [x for x in arr if x > pivot]
|
| 382 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
| 383 |
},
|
| 384 |
"user": "Add Docstring."
|
| 385 |
}
|
|
|
|
| 451 |
|
| 452 |
## Contribution
|
| 453 |
|
| 454 |
+
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.
|