Downloads · 30 days
27
6% of all-time downloads
RichardErkhov/Locutusque_-_TinyMistral-248M-v2-gguf
Locutusque_-_TinyMistral-248M-v2-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
27
6% of all-time downloads
All-time downloads
440
Public
Repo size
2.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf3.4 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
TinyMistral-248M-v2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| TinyMistral-248M-v2.Q2_K.gguf | Q2_K | 0.1GB |
| TinyMistral-248M-v2.IQ3_XS.gguf | IQ3_XS | 0.11GB |
| TinyMistral-248M-v2.IQ3_S.gguf | IQ3_S | 0.11GB |
| TinyMistral-248M-v2.Q3_K_S.gguf | Q3_K_S | 0.11GB |
| TinyMistral-248M-v2.IQ3_M.gguf | IQ3_M | 0.11GB |
| TinyMistral-248M-v2.Q3_K.gguf | Q3_K | 0.12GB |
| TinyMistral-248M-v2.Q3_K_M.gguf | Q3_K_M | 0.12GB |
| TinyMistral-248M-v2.Q3_K_L.gguf | Q3_K_L | 0.13GB |
| TinyMistral-248M-v2.IQ4_XS.gguf | IQ4_XS | 0.13GB |
| TinyMistral-248M-v2.Q4_0.gguf | Q4_0 | 0.14GB |
| TinyMistral-248M-v2.IQ4_NL.gguf | IQ4_NL | 0.14GB |
| TinyMistral-248M-v2.Q4_K_S.gguf | Q4_K_S | 0.14GB |
| TinyMistral-248M-v2.Q4_K.gguf | Q4_K | 0.14GB |
| TinyMistral-248M-v2.Q4_K_M.gguf | Q4_K_M | 0.14GB |
| TinyMistral-248M-v2.Q4_1.gguf | Q4_1 | 0.15GB |
| TinyMistral-248M-v2.Q5_0.gguf | Q5_0 | 0.16GB |
| TinyMistral-248M-v2.Q5_K_S.gguf | Q5_K_S | 0.16GB |
| TinyMistral-248M-v2.Q5_K.gguf | Q5_K | 0.17GB |
| TinyMistral-248M-v2.Q5_K_M.gguf | Q5_K_M | 0.17GB |
| TinyMistral-248M-v2.Q5_1.gguf | Q5_1 | 0.18GB |
| TinyMistral-248M-v2.Q6_K.gguf | Q6_K | 0.19GB |
| TinyMistral-248M-v2.Q8_0.gguf | Q8_0 | 0.25GB |
license: apache-2.0 language:
This model was trained on two datasets, shown in this model page.
You can look at the training metrics here: https://wandb.ai/locutusque/TinyMistral-V2/runs/g0rvw6wc
🔥 This model performed excellently on TruthfulQA, outperforming models more than 720x its size. These models include: mistralai/Mixtral-8x7B-v0.1, tiiuae/falcon-180B, berkeley-nest/Starling-LM-7B-alpha, upstage/SOLAR-10.7B-v1.0, and more. 🔥