Downloads · 30 days
165
19% of all-time downloads
RichardErkhov/vicgalle_-_CarbonBeagle-11B-gguf
vicgalle_-_CarbonBeagle-11B-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
165
19% of all-time downloads
All-time downloads
850
Public
Repo size
108 GB
Likes
0
Public
Click a slice to open those files.
.gguf127 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
CarbonBeagle-11B - GGUF
| Name | Quant method | Size |
|---|---|---|
| CarbonBeagle-11B.Q2_K.gguf | Q2_K | 3.73GB |
| CarbonBeagle-11B.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| CarbonBeagle-11B.Q3_K.gguf | Q3_K | 4.84GB |
| CarbonBeagle-11B.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| CarbonBeagle-11B.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| CarbonBeagle-11B.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| CarbonBeagle-11B.Q4_0.gguf | Q4_0 | 5.66GB |
| CarbonBeagle-11B.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| CarbonBeagle-11B.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| CarbonBeagle-11B.Q4_K.gguf | Q4_K | 6.02GB |
| CarbonBeagle-11B.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| CarbonBeagle-11B.Q4_1.gguf | Q4_1 | 6.27GB |
| CarbonBeagle-11B.Q5_0.gguf | Q5_0 | 6.89GB |
| CarbonBeagle-11B.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| CarbonBeagle-11B.Q5_K.gguf | Q5_K | 7.08GB |
| CarbonBeagle-11B.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| CarbonBeagle-11B.Q5_1.gguf | Q5_1 | 7.51GB |
| CarbonBeagle-11B.Q6_K.gguf | Q6_K | 8.2GB |
| CarbonBeagle-11B.Q8_0.gguf | Q8_0 | 10.62GB |
license: apache-2.0 tags:
An experiment in merging models of different architectures and sizes. Here are the steps:

This model was merged using the linear merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: jeonsworld/CarbonVillain-en-10.7B-v4
parameters:
weight: 1.0
- model: vicgalle/NeuralBeagle-11B
parameters:
weight: 0.5
merge_method: linear
dtype: float16
At the time of its creation (21-01-2024), it is the best model in the Open LLM Leaderboard for its size class (10.7B-11B), and also 13B models:



Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.64 |
| AI2 Reasoning Challenge (25-Shot) | 71.84 |
| HellaSwag (10-Shot) | 88.93 |
| MMLU (5-Shot) | 66.62 |
| TruthfulQA (0-shot) | 69.43 |
| Winogrande (5-shot) | 84.06 |
| GSM8k (5-shot) | 66.94 |
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.36 |
| IFEval (0-Shot) | 54.15 |
| BBH (3-Shot) | 33.06 |
| MATH Lvl 5 (4-Shot) | 5.51 |
| GPQA (0-shot) | 6.94 |
| MuSR (0-shot) | 9.19 |
| MMLU-PRO (5-shot) | 25.29 |