Text Generation
Transformers
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Instructions to use hiiamsid/yi_4k_paged_optimizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hiiamsid/yi_4k_paged_optimizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hiiamsid/yi_4k_paged_optimizer") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hiiamsid/yi_4k_paged_optimizer") model = AutoModelForCausalLM.from_pretrained("hiiamsid/yi_4k_paged_optimizer", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hiiamsid/yi_4k_paged_optimizer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hiiamsid/yi_4k_paged_optimizer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hiiamsid/yi_4k_paged_optimizer", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hiiamsid/yi_4k_paged_optimizer
- SGLang
How to use hiiamsid/yi_4k_paged_optimizer 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 "hiiamsid/yi_4k_paged_optimizer" \ --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": "hiiamsid/yi_4k_paged_optimizer", "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 "hiiamsid/yi_4k_paged_optimizer" \ --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": "hiiamsid/yi_4k_paged_optimizer", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use hiiamsid/yi_4k_paged_optimizer with Docker Model Runner:
docker model run hf.co/hiiamsid/yi_4k_paged_optimizer
Download trainer_state.json from hiiamsid/yi_4k_paged_optimizer: direct link, hf CLI and curl.
- Browser
- Download file 4.36 kB
-
https://huggingface.co/hiiamsid/yi_4k_paged_optimizer/resolve/main/trainer_state.json
- Command line
-
hf download hf://hiiamsid/yi_4k_paged_optimizer/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/hiiamsid/yi_4k_paged_optimizer/resolve/main/trainer_state.json
4.36 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.968, | |
| "eval_steps": 500, | |
| "global_step": 124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9230769230769231e-07, | |
| "loss": 1.9369, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.8461538461538463e-07, | |
| "loss": 1.9166, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.995995873155957e-07, | |
| "loss": 1.8806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.951096619903317e-07, | |
| "loss": 1.7313, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.85719361365271e-07, | |
| "loss": 1.5518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.7161642180652463e-07, | |
| "loss": 1.2057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.9854549169540405, | |
| "eval_runtime": 79.0664, | |
| "eval_samples_per_second": 1.391, | |
| "eval_steps_per_second": 0.177, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.5308279750597144e-07, | |
| "loss": 0.9383, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.3048902348863106e-07, | |
| "loss": 0.6736, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.042868076603638e-07, | |
| "loss": 0.6114, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.75e-07, | |
| "loss": 0.5736, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.4321411944507714e-07, | |
| "loss": 0.5836, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.095646478557912e-07, | |
| "loss": 0.5676, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.569873571395874, | |
| "eval_runtime": 79.9371, | |
| "eval_samples_per_second": 1.376, | |
| "eval_steps_per_second": 0.175, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.747243250910625e-07, | |
| "loss": 0.5831, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.3938969920096296e-07, | |
| "loss": 0.5583, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.0426720063190333e-07, | |
| "loss": 0.5599, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.7005901885718867e-07, | |
| "loss": 0.5424, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.3744906379558164e-07, | |
| "loss": 0.5574, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.0708929268538034e-07, | |
| "loss": 0.5608, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.5596022605895996, | |
| "eval_runtime": 80.1059, | |
| "eval_samples_per_second": 1.373, | |
| "eval_steps_per_second": 0.175, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.958667577511683e-08, | |
| "loss": 0.5648, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 5.5491061420390174e-08, | |
| "loss": 0.551, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.528418319489348e-08, | |
| "loss": 0.5471, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.9370028791882847e-08, | |
| "loss": 0.5572, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 8.066763266625282e-09, | |
| "loss": 0.5416, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.6003680950742726e-09, | |
| "loss": 0.5576, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_loss": 0.5581246018409729, | |
| "eval_runtime": 79.6401, | |
| "eval_samples_per_second": 1.381, | |
| "eval_steps_per_second": 0.176, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "step": 124, | |
| "total_flos": 23406615330816.0, | |
| "train_loss": 0.8594164925236856, | |
| "train_runtime": 9510.8221, | |
| "train_samples_per_second": 0.418, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 124, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 23406615330816.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |