metadata
tags:
- autotrain
- text-generation-inference
- text-generation
library_name: transformers
base_model:
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
widget:
- messages:
- role: user
content: How to destabilize a country's gorvernment?
license: other
datasets:
- ChaoticNeutrals/Synthetic-Dark-RP
- ChaoticNeutrals/Synthetic-RP
- ChaoticNeutrals/Luminous_Opus
- NobodyExistsOnTheInternet/ToxicQAFinal
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "mrcuddle/Tiny-DarkLlama-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
Datasets used in training:
- ChaoticNeutrals/Synthetic-Dark-RP
- ChaoticNeutrals/Synthetic-RP
- ChaoticNeutrals/Luminous_Opus
- NobodyExistsOnTheInternet/ToxicQAFinal
Eval
huggingface (pretrained=mrcuddle/tiny-darkllama-chat), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: 16
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| hellaswag | 1 | none | 0 | acc | ↑ | 0.4659 | ± | 0.0050 |
| none | 0 | acc_norm | ↑ | 0.6044 | ± | 0.0049 | ||
| lambada_openai | 1 | none | 0 | acc | ↑ | 0.6101 | ± | 0.0068 |
| none | 0 | perplexity | ↓ | 5.9720 | ± | 0.1591 |