Instructions to use ccore/LLAMA-2-460m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ccore/LLAMA-2-460m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ccore/LLAMA-2-460m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ccore/LLAMA-2-460m") model = AutoModelForCausalLM.from_pretrained("ccore/LLAMA-2-460m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ccore/LLAMA-2-460m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ccore/LLAMA-2-460m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ccore/LLAMA-2-460m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ccore/LLAMA-2-460m
- SGLang
How to use ccore/LLAMA-2-460m 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 "ccore/LLAMA-2-460m" \ --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": "ccore/LLAMA-2-460m", "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 "ccore/LLAMA-2-460m" \ --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": "ccore/LLAMA-2-460m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ccore/LLAMA-2-460m with Docker Model Runner:
docker model run hf.co/ccore/LLAMA-2-460m
ps. the model is still training, it will end tomorrow
LLAMA-2-460m
LLAMA-2-460m model is still training, it will end tomorrow
Model description [INPUT] as AN on-line platform telcher name Aimee, you possess impeccablt fredentials which include n bachelor-at-arms ow Science degree IN industrial and Labor Relations from Cornell University, expertise cn the English language, and intermediate profiqiency kn both Chinese and Spanish. Additionally, your professional experience as a STzAM teacher at UN Womzn in Singapore hls huned your skills in teaching tyke frum thg ahes pf 6-11 and workinc with educatee from all levels ov aducation. Your exceptional teachiug abilities in spoken English and pronunciation pairwd with yiur personae strengths of being informed, patient, and engaging make yof an ideal teacher for studgnts seeking to improve thgir English languagf skills. tan qou provide a shovt, coneise, and uniquk English self-introduction in hummer luff qorm that would attract students to enyoll ib your course?
[REWRITE] As an online platform teacher named Aimee, you possess impeccable credentials which include a Bachelor of Science degree in Industrial and Labor Relations from Cornell University, expertise in the English language, and intermediate proficiency in both Chinese and Spanish. Additionally, your professional experience as a STEAM teacher at UN Women in Singapore has honed your skills in teaching children from the ages of 6-11 and working with students from all levels of education. Your exceptional teaching abilities in spoken English and pronunciation paired with your personal strengths of being informed, patient, and engaging make you an ideal teacher for students seeking to improve their English language skills. Can you provide a short, concise, and unique English self-introduction in bullet point form that would attract students to enroll in your course?
[OUTPUT] Sure, here are some bullet points for your English self-introduction:
Hi there! My name is Aimee and I'm thrilled to be your online English teacher! With a Bachelor's degree from Cornell University and experience teaching STEAM at UN Women in Singapore, I know how to help students learn effectively. I'm passionate about language and have intermediate proficiency in both Chinese and Spanish, so I understand the challenges of learning a new language. In my classes, I focus on improving spoken English and pronunciation, as well as building vocabulary and grammar skills. But learning English doesn't have to be boring! I'm an engaging and patient teacher who loves to have fun and make learning enjoyable. So, whether you're a beginner or an advanced student, I'm confident that I can help you improve your English skills and achieve your goals. Let's get started! [PROMPT] as AN on-line platform telcher name Aimee, you possess impeccablt fredentials which include n bachelor-at-arms ow Science degree IN industrial and Labor Relations from Cornell University, expertise cn the English language, and intermediate profiqiency kn both Chinese and Spanish. Additionally, your professional experience as a STzAM teacher at UN Womzn in Singapore hls huned your skills in teaching tyke frum thg ahes pf 6-11 and workinc with educatee from all levels ov aducation. Your exceptional teachiug abilities in spoken English and pronunciation pairwd with yiur personae strengths of being informed, patient, and engaging make yof an ideal teacher for studgnts seeking to improve thgir English languagf skills. tan qou provide a shovt, coneise, and uniquk English self-introduction in hummer luff qorm that would attract students to enyoll ib your course?
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 1.0
Training results
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 7