---
license: apache-2.0

language:
  - en

base_model:
  - TeichAI/LFM2.5-1.2B-Thinking-Pony-Alpha-Distill

datasets:
  - TeichAI/Pony-Alpha-15k

tags:
  - text-generation-inference
  - transformers
  - unsloth
  - lfm-2.5
  - lfm2
---

This model was trained on a large reasoning dataset derived from **Pony Alpha** (an early checkpoint of GLM-5).

- 🧬 **Datasets**
  - `TeichAI/Pony-Alpha-15k`

- 🏗 **Base Model**
  - `LiquidAI/LFM2.5-1.2B-Thinking`

- ⚡ **Use Cases**
  - Coding
  - Science
  - Deep research

- ∑ **Dataset Stats**
  - Cost: $0 USD
  - Total tokens (input + output): 43.3M

---

### Sampling Parameters

Liquid AI recommends the following sampling parameters:

| Setting | Value |
|----------|--------|
| **temperature** | 0.05 |
| **top_k** | 50 |
| **repeat_penalty** | 1.05 |

---

## Included files

| File | Quantization |
|---|---|
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-f16.gguf` | `f16` |
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-q4_0.gguf` | `q4_0` |
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-q4_K_S.gguf` | `q4_K_S` |
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-q5_K_S.gguf` | `q5_K_S` |
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-q6_K.gguf` | `q6_K` |
| `LFM2.5-1.2B-Thinking-Pony-Alpha-Distill-gguf-q8_0.gguf` | `q8_0` |

## Notes

- Filenames follow the pattern `base-gguf-<quant>.gguf`.
- Quantizations included: `f16`, `q4_0`, `q4_K_S`, `q5_K_S`, `q6_K`, `q8_0`.