metadata
base_model: mlabonne/NeuralBeagle14-7B
inference: false
license: apache-2.0
model_creator: Maxime Labonne
model_name: NeuralBeagle14 7B
model_type: mistral
pipeline_tag: text-generation
quantized_by: Second State Inc.
tags:
- merge
- mergekit
- lazymergekit
- fblgit/UNA-TheBeagle-7b-v1
- argilla/distilabeled-Marcoro14-7B-slerp
- dpo
- rlhf
NeuralBeagle14-7B-GGUF
Original Model
Run with LlamaEdge
Note that the original model has an potential issue (see the discussion: Model follows ChatML format, but does not have the special tokens for ChatML).
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| NeuralBeagle14-7B-Q2_K.gguf | Q2_K | 2 | 2.72 GB | smallest, significant quality loss - not recommended for most purposes |
| NeuralBeagle14-7B-Q3_K_L.gguf | Q3_K_L | 3 | 3.82 GB | small, substantial quality loss |
| NeuralBeagle14-7B-Q3_K_M.gguf | Q3_K_M | 3 | 3.52 GB | very small, high quality loss |
| NeuralBeagle14-7B-Q3_K_S.gguf | Q3_K_S | 3 | 3.16 GB | very small, high quality loss |
| NeuralBeagle14-7B-Q4_0.ggufs | Q4_0 | 4 | 4.11 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| NeuralBeagle14-7B-Q4_K_M.gguf | Q4_K_M | 4 | 4.37 GB | medium, balanced quality - recommended |
| NeuralBeagle14-7B-Q4_K_S.gguf | Q4_K_S | 4 | 4.14 GB | small, greater quality loss |
| NeuralBeagle14-7B-Q5_0.gguf | Q5_0 | 5 | 5.00 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| NeuralBeagle14-7B-Q5_K_M.gguf | Q5_K_M | 5 | 5.13 GB | large, very low quality loss - recommended |
| NeuralBeagle14-7B-Q5_K_S.gguf | Q5_K_S | 5 | 5.00 GB | large, low quality loss - recommended |
| NeuralBeagle14-7B-Q6_K.gguf | Q6_K | 6 | 5.94 GB | very large, extremely low quality loss |
| NeuralBeagle14-7B-Q8_0.gguf | Q8_0 | 8 | 7.70 GB | very large, extremely low quality loss - not recommended |