MicroLlama-134M-Instruct is a custom-trained Small Language Model (SLM) created by Abhiray (Jay). Built using a scaled-down Llama architecture, this model is designed to be highly efficient, lightweight, and can try to conversational instruction-following.
This model was trained entirely from scratch in three distinct phases:
Phase 1 & 2: Continuous Pre-Training (CPT):
Trained on ~9 Billion tokens of high-quality web, educational, and narrative data.
Phase 3: Supervised Fine-Tuning (SFT):
Fine-tuned for 250 high-precision steps using
-100
target masking.
💻 How to Use
The model strictly follows the ChatML-style template used during its SFT phase. For optimal performance, a generation
temperature
between
0.3
and
0.5
with a gentle
repetition_penalty
(e.g., 1.05) is recommended.
Prompt Format:
<|system|>
You are a highly capable, friendly, and helpful AI assistant.</s>
<|user|>
What is the core temperature of the Sun?</s>
<|assistant|>
Runs of Abiray MicroLlama-134M-Instruct on huggingface.co
34
Total runs
2
24-hour runs
2
3-day runs
5
7-day runs
10
30-day runs
More Information About MicroLlama-134M-Instruct huggingface.co Model
MicroLlama-134M-Instruct huggingface.co is an AI model on huggingface.co that provides MicroLlama-134M-Instruct's model effect (), which can be used instantly with this Abiray MicroLlama-134M-Instruct model. huggingface.co supports a free trial of the MicroLlama-134M-Instruct model, and also provides paid use of the MicroLlama-134M-Instruct. Support call MicroLlama-134M-Instruct model through api, including Node.js, Python, http.
MicroLlama-134M-Instruct huggingface.co is an online trial and call api platform, which integrates MicroLlama-134M-Instruct's modeling effects, including api services, and provides a free online trial of MicroLlama-134M-Instruct, you can try MicroLlama-134M-Instruct online for free by clicking the link below.
Abiray MicroLlama-134M-Instruct online free url in huggingface.co:
MicroLlama-134M-Instruct is an open source model from GitHub that offers a free installation service, and any user can find MicroLlama-134M-Instruct on GitHub to install. At the same time, huggingface.co provides the effect of MicroLlama-134M-Instruct install, users can directly use MicroLlama-134M-Instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
MicroLlama-134M-Instruct install url in huggingface.co: