Downloads · 30 days
288
14% of all-time downloads
RichardErkhov/mlabonne_-_GML-Mistral-merged-v1-gguf
mlabonne_-_GML-Mistral-merged-v1-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
288
14% of all-time downloads
All-time downloads
2.1K
Public
Repo size
102 GB
Likes
0
Public
Click a slice to open those files.
.gguf118 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
GML-Mistral-merged-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| GML-Mistral-merged-v1.Q2_K.gguf | Q2_K | 3.13GB |
| GML-Mistral-merged-v1.IQ3_XS.gguf | IQ3_XS | 3.48GB |
| GML-Mistral-merged-v1.IQ3_S.gguf | IQ3_S | 3.67GB |
| GML-Mistral-merged-v1.Q3_K_S.gguf | Q3_K_S | 3.65GB |
| GML-Mistral-merged-v1.IQ3_M.gguf | IQ3_M | 3.79GB |
| GML-Mistral-merged-v1.Q3_K.gguf | Q3_K | 4.05GB |
| GML-Mistral-merged-v1.Q3_K_M.gguf | Q3_K_M | 4.05GB |
| GML-Mistral-merged-v1.Q3_K_L.gguf | Q3_K_L | 4.41GB |
| GML-Mistral-merged-v1.IQ4_XS.gguf | IQ4_XS | 4.55GB |
| GML-Mistral-merged-v1.Q4_0.gguf | Q4_0 | 4.74GB |
| GML-Mistral-merged-v1.IQ4_NL.gguf | IQ4_NL | 4.79GB |
| GML-Mistral-merged-v1.Q4_K_S.gguf | Q4_K_S | 4.78GB |
| GML-Mistral-merged-v1.Q4_K.gguf | Q4_K | 5.04GB |
| GML-Mistral-merged-v1.Q4_K_M.gguf | Q4_K_M | 5.04GB |
| GML-Mistral-merged-v1.Q4_1.gguf | Q4_1 | 5.26GB |
| GML-Mistral-merged-v1.Q5_0.gguf | Q5_0 | 5.77GB |
| GML-Mistral-merged-v1.Q5_K_S.gguf | Q5_K_S | 5.77GB |
| GML-Mistral-merged-v1.Q5_K.gguf | Q5_K | 5.93GB |
| GML-Mistral-merged-v1.Q5_K_M.gguf | Q5_K_M | 5.93GB |
| GML-Mistral-merged-v1.Q5_1.gguf | Q5_1 | 6.29GB |
| GML-Mistral-merged-v1.Q6_K.gguf | Q6_K | 6.87GB |
| GML-Mistral-merged-v1.Q8_0.gguf | Q8_0 | 8.89GB |
license: apache-2.0 tags:
Quick attempt to reproduce zyh3826/GML-Mistral-merged-v1.
This model is a merge of the following models made with mergekit:
slices:
- sources:
- model: quantumaikr/quantum-v0.01
layer_range: [0, 32]
- sources:
- model: mncai/mistral-7b-dpo-v5
layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 48.54 |
| AI2 Reasoning Challenge (25-Shot) | 43.77 |
| HellaSwag (10-Shot) | 57.89 |
| MMLU (5-Shot) | 64.13 |
| TruthfulQA (0-shot) | 51.58 |
| Winogrande (5-shot) | 73.88 |
| GSM8k (5-shot) | 0.00 |