bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update metadata with huggingface_hub

Browse Source
This commit is contained in:
ai-modelscope
2025-07-08 22:16:42 +08:00
parent 160fbee502
commit dd4923132b
30 changed files with 92 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@@ -1,14 +1,14 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license: apache-2.0
base_model_relation: quantized
base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
base_model_relation: quantized
license: apache-2.0
---
## Llamacpp imatrix Quantizations of Dolphin-Mistral-24B-Venice-Edition by cognitivecomputations
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5317">b5317</a> for quantization.
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5835">b5835</a> for quantization.
Original model: https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
@@ -24,6 +24,10 @@ Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or a
<s>[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST]
```
## What's new:
Original model updated
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
@@ -54,6 +58,7 @@ Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or a
| [Dolphin-Mistral-24B-Venice-Edition-IQ2_M.gguf](https://huggingface.co/bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF/blob/main/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Dolphin-Mistral-24B-Venice-Edition-IQ2_S.gguf](https://huggingface.co/bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF/blob/main/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. |
| [Dolphin-Mistral-24B-Venice-Edition-IQ2_XS.gguf](https://huggingface.co/bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF/blob/main/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-IQ2_XS.gguf) | IQ2_XS | 7.21GB | false | Low quality, uses SOTA techniques to be usable. |
| [Dolphin-Mistral-24B-Venice-Edition-IQ2_XXS.gguf](https://huggingface.co/bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF/blob/main/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-IQ2_XXS.gguf) | IQ2_XXS | 6.55GB | false | Very low quality, uses SOTA techniques to be usable. |
## Embed/output weights