File size: 1,667 Bytes
13a70d4 d1194ad 13a70d4 322fd97 13a70d4 322fd97 13a70d4 d1194ad |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
---
pipeline_tag: text-generation
---
# Model Card for Model ID
Small testing version of my first model
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
Test version of my first model
## Uses
Dosen't work well
### Out-of-Scope Use
Better not use for anything
[More Information Needed]
## Bias, Risks, and Limitations
Don't work
## How to Get Started with the Model
```import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load pre-trained model tokenizer (v3 compatibility)
tokenizer = AutoTokenizer.from_pretrained("amusktweewt/14M-small-chat")
# Load pre-trained model (PyTorch Lightning module)
model = AutoModelForCausalLM.from_pretrained("amusktweewt/14M-small-chat")
# Set device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
while True:
user_input = input("> ")
if user_input.lower() == "quit":
break
inputs = tokenizer(user_input, return_tensors="pt", max_length=512, truncation=True).to(device)
outputs = model(**inputs)
logits = outputs.logits
probs = torch.nn.functional.softmax(logits, dim=-1)
top_prob, top_idx = torch.topk(probs, 3) # Get the top 3 probabilities
# Flatten the list of token IDs before decoding
top_idx = top_idx[0].view(-1).tolist()
top_pred = tokenizer.decode(top_idx, skip_special_tokens=True)
print(f"You: {user_input}")
print(f"Model: {top_pred}")
print("Goodbye!")
``` |