Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ language:
|
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
---
|
| 16 |
|
| 17 |
-
# Micro-Merlin
|
| 18 |
|
| 19 |
This is a fine-tune of **LiquidAI/LFM2.5-1.2B-Thinking** on GPT-5.2 reasoning traces.
|
| 20 |
|
|
@@ -57,7 +57,7 @@ The model was trained with LoRA on the [TeichAI/gpt-5.2-high-reasoning-250x](htt
|
|
| 57 |
from unsloth import FastLanguageModel
|
| 58 |
|
| 59 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
| 60 |
-
model_name="OrionLLM/Micro-Merlin",
|
| 61 |
max_seq_length=20480,
|
| 62 |
load_in_4bit=False,
|
| 63 |
)
|
|
@@ -74,5 +74,12 @@ print(tokenizer.decode(out[0], skip_special_tokens=True))
|
|
| 74 |
|
| 75 |
---
|
| 76 |
|
|
|
|
|
|
|
| 77 |
**Merlin Research • 2026**
|
|
|
|
|
|
|
|
|
|
| 78 |
Developed by [DedeProGames](https://huggingface.co/DedeProGames)
|
|
|
|
|
|
|
|
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# Micro-Merlin-Experimental
|
| 18 |
|
| 19 |
This is a fine-tune of **LiquidAI/LFM2.5-1.2B-Thinking** on GPT-5.2 reasoning traces.
|
| 20 |
|
|
|
|
| 57 |
from unsloth import FastLanguageModel
|
| 58 |
|
| 59 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
| 60 |
+
model_name="OrionLLM/Micro-Merlin-Experimental",
|
| 61 |
max_seq_length=20480,
|
| 62 |
load_in_4bit=False,
|
| 63 |
)
|
|
|
|
| 74 |
|
| 75 |
---
|
| 76 |
|
| 77 |
+
<div align="center">
|
| 78 |
+
|
| 79 |
**Merlin Research • 2026**
|
| 80 |
+
|
| 81 |
+
<br>
|
| 82 |
+
|
| 83 |
Developed by [DedeProGames](https://huggingface.co/DedeProGames)
|
| 84 |
+
|
| 85 |
+
</div>
|