Text Classification
Transformers
Safetensors
GGUF
English
bert
email
triage
classification
specific-ai
text-embeddings-inference
feature-extraction
Instructions to use specific-AI/email-agent-triage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use specific-AI/email-agent-triage with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="specific-AI/email-agent-triage")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("specific-AI/email-agent-triage") model = AutoModelForSequenceClassification.from_pretrained("specific-AI/email-agent-triage", device_map="auto") - llama-cpp-python
How to use specific-AI/email-agent-triage with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="specific-AI/email-agent-triage", filename="bert-base-only.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use specific-AI/email-agent-triage with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf specific-AI/email-agent-triage # Run inference directly in the terminal: llama cli -hf specific-AI/email-agent-triage
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf specific-AI/email-agent-triage # Run inference directly in the terminal: llama cli -hf specific-AI/email-agent-triage
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf specific-AI/email-agent-triage # Run inference directly in the terminal: ./llama-cli -hf specific-AI/email-agent-triage
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf specific-AI/email-agent-triage # Run inference directly in the terminal: ./build/bin/llama-cli -hf specific-AI/email-agent-triage
Use Docker
docker model run hf.co/specific-AI/email-agent-triage
- LM Studio
- Jan
- Ollama
How to use specific-AI/email-agent-triage with Ollama:
ollama run hf.co/specific-AI/email-agent-triage
- Unsloth Studio
How to use specific-AI/email-agent-triage with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for specific-AI/email-agent-triage to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for specific-AI/email-agent-triage to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for specific-AI/email-agent-triage to start chatting
- Atomic Chat new
- Docker Model Runner
How to use specific-AI/email-agent-triage with Docker Model Runner:
docker model run hf.co/specific-AI/email-agent-triage
- Lemonade
How to use specific-AI/email-agent-triage with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull specific-AI/email-agent-triage
Run and chat with the model
lemonade run user.email-agent-triage-{{QUANT_TAG}}List all available models
lemonade list
| { | |
| "best_global_step": 3136, | |
| "best_metric": 0.8876387938129007, | |
| "best_model_checkpoint": "/app/checkpoints/checkpoint-3136", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 3136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_accuracy": 0.43732057416267944, | |
| "eval_class_metrics": { | |
| "0": { | |
| "accuracy": 0.9419457735247209, | |
| "confusion_matrix": { | |
| "fn": 182, | |
| "fp": 0, | |
| "tn": 2953, | |
| "tp": 0 | |
| }, | |
| "f_beta_score": 0.0, | |
| "precision": 0, | |
| "recall": 0.0 | |
| }, | |
| "1": { | |
| "accuracy": 0.7435406698564593, | |
| "confusion_matrix": { | |
| "fn": 803, | |
| "fp": 1, | |
| "tn": 2331, | |
| "tp": 0 | |
| }, | |
| "f_beta_score": 0.0, | |
| "precision": 0.0, | |
| "recall": 0.0 | |
| }, | |
| "2": { | |
| "accuracy": 0.9151515151515152, | |
| "confusion_matrix": { | |
| "fn": 266, | |
| "fp": 0, | |
| "tn": 2869, | |
| "tp": 0 | |
| }, | |
| "f_beta_score": 0.0, | |
| "precision": 0, | |
| "recall": 0.0 | |
| }, | |
| "3": { | |
| "accuracy": 0.4376395534290271, | |
| "confusion_matrix": { | |
| "fn": 1, | |
| "fp": 1762, | |
| "tn": 1, | |
| "tp": 1371 | |
| }, | |
| "f_beta_score": 0.6086570477247503, | |
| "precision": 0.43759974465368656, | |
| "recall": 0.999271137026239 | |
| }, | |
| "4": { | |
| "accuracy": 0.8363636363636363, | |
| "confusion_matrix": { | |
| "fn": 512, | |
| "fp": 1, | |
| "tn": 2622, | |
| "tp": 0 | |
| }, | |
| "f_beta_score": 0.0, | |
| "precision": 0.0, | |
| "recall": 0.0 | |
| } | |
| }, | |
| "eval_confusion_matrix": { | |
| "fn": 1764, | |
| "fp": 1764, | |
| "tn": 10776, | |
| "tp": 1371 | |
| }, | |
| "eval_f_beta_score": 0.26637239855768974, | |
| "eval_label_confusion_matrix": { | |
| "labels": [ | |
| "FYI", | |
| "NEEDS_RESPONSE", | |
| "PERSONAL", | |
| "PROMOTIONAL", | |
| "URGENT" | |
| ], | |
| "matrix": [ | |
| [ | |
| 0, | |
| 1, | |
| 0, | |
| 181, | |
| 0 | |
| ], | |
| [ | |
| 0, | |
| 0, | |
| 0, | |
| 803, | |
| 0 | |
| ], | |
| [ | |
| 0, | |
| 0, | |
| 0, | |
| 266, | |
| 0 | |
| ], | |
| [ | |
| 0, | |
| 0, | |
| 0, | |
| 1371, | |
| 1 | |
| ], | |
| [ | |
| 0, | |
| 0, | |
| 0, | |
| 512, | |
| 0 | |
| ] | |
| ] | |
| }, | |
| "eval_loss": 1.6771581172943115, | |
| "eval_precision": 0.1915109568308957, | |
| "eval_recall": 0.43732057416267944, | |
| "eval_runtime": 18.7918, | |
| "eval_sample_size": 3135, | |
| "eval_samples_per_second": 166.828, | |
| "eval_steps_per_second": 20.86, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 100.88322448730469, | |
| "hard_loss": 0.6793025164542439, | |
| "learning_rate": 4.3964845118848066e-05, | |
| "loss": 0.6793, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8650717703349282, | |
| "eval_class_metrics": { | |
| "0": { | |
| "accuracy": 0.9639553429027113, | |
| "confusion_matrix": { | |
| "fn": 65, | |
| "fp": 48, | |
| "tn": 2905, | |
| "tp": 117 | |
| }, | |
| "f_beta_score": 0.6743515850144092, | |
| "precision": 0.7090909090909091, | |
| "recall": 0.6428571428571429 | |
| }, | |
| "1": { | |
| "accuracy": 0.9036682615629984, | |
| "confusion_matrix": { | |
| "fn": 167, | |
| "fp": 135, | |
| "tn": 2197, | |
| "tp": 636 | |
| }, | |
| "f_beta_score": 0.8081321473951716, | |
| "precision": 0.8249027237354085, | |
| "recall": 0.7920298879202988 | |
| }, | |
| "2": { | |
| "accuracy": 0.9808612440191388, | |
| "confusion_matrix": { | |
| "fn": 21, | |
| "fp": 39, | |
| "tn": 2830, | |
| "tp": 245 | |
| }, | |
| "f_beta_score": 0.8909090909090909, | |
| "precision": 0.8626760563380281, | |
| "recall": 0.9210526315789473 | |
| }, | |
| "3": { | |
| "accuracy": 0.9502392344497608, | |
| "confusion_matrix": { | |
| "fn": 101, | |
| "fp": 55, | |
| "tn": 1708, | |
| "tp": 1271 | |
| }, | |
| "f_beta_score": 0.9421793921423276, | |
| "precision": 0.9585218702865762, | |
| "recall": 0.9263848396501457 | |
| }, | |
| "4": { | |
| "accuracy": 0.9314194577352473, | |
| "confusion_matrix": { | |
| "fn": 69, | |
| "fp": 146, | |
| "tn": 2477, | |
| "tp": 443 | |
| }, | |
| "f_beta_score": 0.8047229791099001, | |
| "precision": 0.7521222410865874, | |
| "recall": 0.865234375 | |
| } | |
| }, | |
| "eval_confusion_matrix": { | |
| "fn": 423, | |
| "fp": 423, | |
| "tn": 12117, | |
| "tp": 2712 | |
| }, | |
| "eval_f_beta_score": 0.8654967184485823, | |
| "eval_label_confusion_matrix": { | |
| "labels": [ | |
| "FYI", | |
| "NEEDS_RESPONSE", | |
| "PERSONAL", | |
| "PROMOTIONAL", | |
| "URGENT" | |
| ], | |
| "matrix": [ | |
| [ | |
| 117, | |
| 36, | |
| 4, | |
| 20, | |
| 5 | |
| ], | |
| [ | |
| 40, | |
| 636, | |
| 10, | |
| 19, | |
| 98 | |
| ], | |
| [ | |
| 1, | |
| 5, | |
| 245, | |
| 7, | |
| 8 | |
| ], | |
| [ | |
| 6, | |
| 59, | |
| 1, | |
| 1271, | |
| 35 | |
| ], | |
| [ | |
| 1, | |
| 35, | |
| 24, | |
| 9, | |
| 443 | |
| ] | |
| ] | |
| }, | |
| "eval_loss": 0.5608769059181213, | |
| "eval_precision": 0.8679750740253618, | |
| "eval_recall": 0.8650717703349282, | |
| "eval_runtime": 19.0243, | |
| "eval_sample_size": 3135, | |
| "eval_samples_per_second": 164.789, | |
| "eval_steps_per_second": 20.605, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 21.096660614013672, | |
| "hard_loss": 0.4585136638052063, | |
| "learning_rate": 4.165098356927757e-05, | |
| "loss": 0.4585, | |
| "step": 3136 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8902711323763955, | |
| "eval_class_metrics": { | |
| "0": { | |
| "accuracy": 0.9728867623604466, | |
| "confusion_matrix": { | |
| "fn": 69, | |
| "fp": 16, | |
| "tn": 2937, | |
| "tp": 113 | |
| }, | |
| "f_beta_score": 0.7266881028938906, | |
| "precision": 0.875968992248062, | |
| "recall": 0.6208791208791209 | |
| }, | |
| "1": { | |
| "accuracy": 0.9247208931419457, | |
| "confusion_matrix": { | |
| "fn": 121, | |
| "fp": 115, | |
| "tn": 2217, | |
| "tp": 682 | |
| }, | |
| "f_beta_score": 0.8525, | |
| "precision": 0.8557089084065245, | |
| "recall": 0.8493150684931506 | |
| }, | |
| "2": { | |
| "accuracy": 0.980542264752791, | |
| "confusion_matrix": { | |
| "fn": 23, | |
| "fp": 38, | |
| "tn": 2831, | |
| "tp": 243 | |
| }, | |
| "f_beta_score": 0.8884826325411335, | |
| "precision": 0.8647686832740213, | |
| "recall": 0.9135338345864662 | |
| }, | |
| "3": { | |
| "accuracy": 0.9569377990430622, | |
| "confusion_matrix": { | |
| "fn": 26, | |
| "fp": 109, | |
| "tn": 1654, | |
| "tp": 1346 | |
| }, | |
| "f_beta_score": 0.9522461973823841, | |
| "precision": 0.925085910652921, | |
| "recall": 0.9810495626822158 | |
| }, | |
| "4": { | |
| "accuracy": 0.9454545454545454, | |
| "confusion_matrix": { | |
| "fn": 105, | |
| "fp": 66, | |
| "tn": 2557, | |
| "tp": 407 | |
| }, | |
| "f_beta_score": 0.8263959390862944, | |
| "precision": 0.8604651162790697, | |
| "recall": 0.794921875 | |
| } | |
| }, | |
| "eval_confusion_matrix": { | |
| "fn": 344, | |
| "fp": 344, | |
| "tn": 12196, | |
| "tp": 2791 | |
| }, | |
| "eval_f_beta_score": 0.8876387938129007, | |
| "eval_label_confusion_matrix": { | |
| "labels": [ | |
| "FYI", | |
| "NEEDS_RESPONSE", | |
| "PERSONAL", | |
| "PROMOTIONAL", | |
| "URGENT" | |
| ], | |
| "matrix": [ | |
| [ | |
| 113, | |
| 47, | |
| 2, | |
| 19, | |
| 1 | |
| ], | |
| [ | |
| 8, | |
| 682, | |
| 12, | |
| 58, | |
| 43 | |
| ], | |
| [ | |
| 0, | |
| 8, | |
| 243, | |
| 6, | |
| 9 | |
| ], | |
| [ | |
| 6, | |
| 6, | |
| 1, | |
| 1346, | |
| 13 | |
| ], | |
| [ | |
| 2, | |
| 54, | |
| 23, | |
| 26, | |
| 407 | |
| ] | |
| ] | |
| }, | |
| "eval_loss": 0.5647311210632324, | |
| "eval_precision": 0.8887926917834664, | |
| "eval_recall": 0.8902711323763955, | |
| "eval_runtime": 19.121, | |
| "eval_sample_size": 3135, | |
| "eval_samples_per_second": 163.956, | |
| "eval_steps_per_second": 20.501, | |
| "step": 3136 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 31360, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5962158438930816.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |