GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mario-rc
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mario-rc
Model Tree
microsoft/DialoGPT-small
Input Modalities
Output Modalities
Supported Functionality
microsoft/DialoGPT-smallGPT2LMHeadModel| Model | Base model | Parameters | Evaluation perplexity |
|---|---|---|---|
| Emotional DistilGPT2 | distilgpt2 | 81.9M | 15.3322 |
| Emotional GPT-2 | gpt2 | 124.4M | 12.9404 |
| Emotional GPT-2 Medium | gpt2-medium | 354.8M | 10.0080 |
| Emotional GPT-2 Large | gpt2-large | 774.0M | 7.4115 |
| Emotional DialoGPT Small | microsoft/DialoGPT-small | 124.4M | 13.0488 |
| Emotional DialoGPT Medium | microsoft/DialoGPT-medium | 354.8M | 10.5130 |
| Emotional DialoGPT Large | microsoft/DialoGPT-large | 774.0M | 8.6719 |
The fine-tuning run used the following setup:
data/gpt-dialogues/train.txt; evaluation data: data/gpt-dialogues/dev.txt, built from DailyDialog CSV resources1e-51.042Training examples use adjacent DailyDialog utterance pairs with explicit source and target emotion labels:
text
<bos><source_emotion>source utterance<sep><target_emotion>target utterance<|endoftext|>At generation time, the prompt should include the source utterance and the desired target emotion:
text
<bos><source_emotion>source utterance<sep><target_emotion>Prompt and training tags:
<bos> marks the beginning of one formatted dialogue example.<source_emotion> is a placeholder for one emotion label describing the input/source utterance, for example <fear>.source utterance is the user/input text.<sep> separates the source side from the response side.<target_emotion> is a placeholder for the emotion you want the generated response to follow, for example <happiness>.target utterance is the response text generated by the model.<|endoftext|> marks the end of one example. GPT-2 uses this as its native end-of-text/eos token, and generation can stop when this token is produced.Emotion conditioning: replace <source_emotion> and <target_emotion> in the
template with one of the model's literal emotion tokens in each position.
Supported emotion labels:
<no emotion><anger><disgust><fear><happiness><sadness><surprise>For example:
text
<bos><fear>I just started a new job and I am a bit nervous.<sep><happiness>This means: the source utterance expresses fear, and the requested response
should be conditioned toward happiness.
python
from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "mario-rc/emotional-dialogpt-small" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id)model.config.pad_token_id = tokenizer.pad_token_id prompt = "<bos><fear>I just started a new job and I am a bit nervous.<sep><happiness>"inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate( **inputs, do_sample=True, max_new_tokens=80, temperature=0.8, top_p=0.95, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id,) generated = outputs[0][inputs["input_ids"].shape[-1]:]response = tokenizer.decode(generated, skip_special_tokens=False)response = response.split(tokenizer.eos_token, 1)[0].strip() emotion_labels = [ "<no emotion>", "<anger>", "<disgust>", "<fear>", "<happiness>", "<sadness>", "<surprise>",] for label in emotion_labels: if response.startswith(label): response = response[len(label):].strip() break print(response)The model is intended for experimental dialogue/text generation. Generated text may be inaccurate, biased, repetitive, or emotionally inappropriate, and should be reviewed before user-facing use.
from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "mario-rc/emotional-dialogpt-small" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id)model.config.pad_token_id = tokenizer.pad_token_id prompt = "<bos><fear>I just started a new job and I am a bit nervous.<sep><happiness>"inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate( **inputs, do_sample=True, max_new_tokens=80, temperature=0.8, top_p=0.95, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id,) generated = outputs[0][inputs["input_ids"].shape[-1]:]response = tokenizer.decode(generated, skip_special_tokens=False)response = response.split(tokenizer.eos_token, 1)[0].strip() emotion_labels = [ "<no emotion>", "<anger>", "<disgust>", "<fear>", "<happiness>", "<sadness>", "<surprise>",] for label in emotion_labels: if response.startswith(label): response = response[len(label):].strip() break print(response)