Instructions to use ElMater06/VSCD-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ElMater06/VSCD-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ElMater06/VSCD-2b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ElMater06/VSCD-2b") model = AutoModelForCausalLM.from_pretrained("ElMater06/VSCD-2b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ElMater06/VSCD-2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ElMater06/VSCD-2b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ElMater06/VSCD-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ElMater06/VSCD-2b
- SGLang
How to use ElMater06/VSCD-2b 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 "ElMater06/VSCD-2b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ElMater06/VSCD-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "ElMater06/VSCD-2b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ElMater06/VSCD-2b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ElMater06/VSCD-2b with Docker Model Runner:
docker model run hf.co/ElMater06/VSCD-2b
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,7 @@ tags:
|
|
| 8 |
- unsloth
|
| 9 |
- gemma
|
| 10 |
- trl
|
| 11 |
-
|
| 12 |
-
- Edit this users input to make it search for relevant keywords online. Only respond with the new string of optimized text. ### Instruction: {Query_To_Summarize} ### Response:```
|
| 13 |
base_model: unsloth/gemma-2b-it-bnb-4bit
|
| 14 |
datasets:
|
| 15 |
- ElMater06/VSCD-dataset
|
|
@@ -24,7 +23,9 @@ pipeline_tag: conversational
|
|
| 24 |
|
| 25 |
|
| 26 |
|
|
|
|
| 27 |
|
|
|
|
| 28 |
- VSCD-2b is a large language model trained on search queries and summarized search queries.
|
| 29 |
- VSCD was trained on a synthetic dataset based off the Gemma-2b-IT model which contained 300 entries for 9 epochs, It was made to provide fast summarization of a user's query to make searching algorithms faster.
|
| 30 |
- **Developed by:** ElMater06
|
|
|
|
| 8 |
- unsloth
|
| 9 |
- gemma
|
| 10 |
- trl
|
| 11 |
+
|
|
|
|
| 12 |
base_model: unsloth/gemma-2b-it-bnb-4bit
|
| 13 |
datasets:
|
| 14 |
- ElMater06/VSCD-dataset
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
|
| 26 |
+
-**Prompt Format: Alpaca**
|
| 27 |
|
| 28 |
+
- ```Edit this users input to make it search for relevant keywords online. Only respond with the new string of optimized text. ### Instruction: {Query_To_Summarize} ### Response:```
|
| 29 |
- VSCD-2b is a large language model trained on search queries and summarized search queries.
|
| 30 |
- VSCD was trained on a synthetic dataset based off the Gemma-2b-IT model which contained 300 entries for 9 epochs, It was made to provide fast summarization of a user's query to make searching algorithms faster.
|
| 31 |
- **Developed by:** ElMater06
|