Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Locutusque/TinyMistral-248M
|
| 3 |
+
datasets:
|
| 4 |
+
- Skylion007/openwebtext
|
| 5 |
+
inference: false
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
model_creator: Locutusque
|
| 10 |
+
model_name: TinyMistral-248M
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
quantized_by: afrideva
|
| 13 |
+
tags:
|
| 14 |
+
- gguf
|
| 15 |
+
- ggml
|
| 16 |
+
- quantized
|
| 17 |
+
- q2_k
|
| 18 |
+
- q3_k_m
|
| 19 |
+
- q4_k_m
|
| 20 |
+
- q5_k_m
|
| 21 |
+
- q6_k
|
| 22 |
+
- q8_0
|
| 23 |
+
---
|
| 24 |
+
# Locutusque/TinyMistral-248M-GGUF
|
| 25 |
+
|
| 26 |
+
Quantized GGUF model files for [TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M) from [Locutusque](https://huggingface.co/Locutusque)
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
| Name | Quant method | Size |
|
| 30 |
+
| ---- | ---- | ---- |
|
| 31 |
+
| [tinymistral-248m.q2_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q2_k.gguf) | q2_k | 115.26 MB |
|
| 32 |
+
| [tinymistral-248m.q3_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q3_k_m.gguf) | q3_k_m | 130.08 MB |
|
| 33 |
+
| [tinymistral-248m.q4_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q4_k_m.gguf) | q4_k_m | 155.67 MB |
|
| 34 |
+
| [tinymistral-248m.q5_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q5_k_m.gguf) | q5_k_m | 179.23 MB |
|
| 35 |
+
| [tinymistral-248m.q6_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q6_k.gguf) | q6_k | 204.26 MB |
|
| 36 |
+
| [tinymistral-248m.q8_0.gguf](https://huggingface.co/afrideva/TinyMistral-248M-GGUF/resolve/main/tinymistral-248m.q8_0.gguf) | q8_0 | 264.32 MB |
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Original Model Card:
|
| 41 |
+
A pre-trained language model, based on the Mistral 7B model, has been scaled down to approximately 248 million parameters. Currently, it's been trained on 250,000 examples over 125,000 steps within the first epoch. The batch size is ramped up from 2 to 16 for future epochs. This model isn't intended for direct use but for fine-tuning on a downstream task.
|
| 42 |
+
|
| 43 |
+
During evaluation on InstructMix, this model achieved an average perplexity score of 6.3. More training sessions are planned for this model.
|