NovatasticRoScript commited on
Commit
c31a98a
·
verified ·
1 Parent(s): 03efae3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - mini-llm
10
  - text-generation-inference
11
  - lm-evaluation-harness
 
12
  datasets:
13
  - openai/gsm8k
14
  - openai/openai_humaneval
@@ -91,7 +92,7 @@ model-index:
91
  <img src="OfficialAtomight.png" alt="Atomight Logo" width="500" style="max-width: 100%;">
92
  </p>
93
 
94
- **Atomight-V2.1-0.5B-Inference** is an ultra-compact, reasoning-oriented causal language model developed under the **[Atomight Ecosystem](https://huggingface.co/NovatasticRoScript/collections)**. Built on a Qwen-derived 494M parameter foundation, the model has been refined using **GRPO (Group Relative Policy Optimization)** reinforcement tuning.
95
 
96
  Despite its tiny physical footprint, Atomight-V2.1-0.5B targets highly efficient edge-device reasoning, structured text outputs, lightweight coding assistance, and rapid deployment workflows under severe compute constraints.
97
 
 
9
  - mini-llm
10
  - text-generation-inference
11
  - lm-evaluation-harness
12
+ - atomight
13
  datasets:
14
  - openai/gsm8k
15
  - openai/openai_humaneval
 
92
  <img src="OfficialAtomight.png" alt="Atomight Logo" width="500" style="max-width: 100%;">
93
  </p>
94
 
95
+ **Atomight-V2.1-0.5B-Inference** is an ultra-compact, reasoning-oriented causal language model developed under the **[Atomight Ecosystem](https://huggingface.co/NovatasticRoScript/collections)**. Currently our **best model** up-to-date. Built on a Qwen-derived 494M parameter foundation, the model has been refined using **GRPO (Group Relative Policy Optimization)** reinforcement tuning.
96
 
97
  Despite its tiny physical footprint, Atomight-V2.1-0.5B targets highly efficient edge-device reasoning, structured text outputs, lightweight coding assistance, and rapid deployment workflows under severe compute constraints.
98