Downloads · 30 days
98
17% of all-time downloads
reallexi/lexi-rm-agent
lexi-rm-agent is a text generation model from reallexi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
A standalone model of 495M parameters, derived from Qwen/Qwen2.5-0.5B-Instruct.
Downloads · 30 days
98
17% of all-time downloads
All-time downloads
580
Public
Parameters
494M
2.9 GB on disk
Likes
2
Public
Click a slice to open those files.
.gguf1.9 GB · 66%
From the Hugging Face model README
A standalone model of 495M parameters, derived from Qwen/Qwen2.5-0.5B-Instruct.
The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime.
| Parameters | 495,114,112 (495M) |
| Weights on disk | 953 MB |
| Trained context length | 512 tokens |
| Base model | Qwen/Qwen2.5-0.5B-Instruct |
Approximate memory to hold the weights. Add context and runtime overhead on top.
| Precision | Weights |
|---|---|
| FP16 / BF16 | 944 MB |
| 8-bit (Q8_0) | 472 MB |
| 4-bit (Q4_K_M) | 260 MB |
| Strategy | slm |
| Adapter | Auto LoRA |
| LoRA rank / alpha | 8 / 16 |
| Dataset | bitext/Bitext-customer-support-llm-chatbot-training-dataset |
| Samples learned | 100,000 (through phase 382 of 382) |
| Training steps | 1,250 |
| Epochs | 5 |
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("reallexi/lexi-rm-agent")
tokenizer = AutoTokenizer.from_pretrained("reallexi/lexi-rm-agent")
The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.
Base model: Qwen/Qwen2.5-0.5B-Instruct
Training data: bitext/Bitext-customer-support-llm-chatbot-training-dataset
Copyright (c) 2026 Reallexi LLC. All rights reserved.
Produced by Reallexi LLC AI Model Builder from training job #1272. Core: https://llm.reallexi.io