Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,60 @@ tags:
|
|
| 16 |
- visual-understanding
|
| 17 |
- caption
|
| 18 |
- image-to-text
|
| 19 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
- visual-understanding
|
| 17 |
- caption
|
| 18 |
- image-to-text
|
| 19 |
+
---
|
| 20 |
+
# **Qwen3-VL-8B-Abliterated-Caption-it-GGUF**
|
| 21 |
+
|
| 22 |
+
> The Qwen3-VL-8B-Abliterated-Caption-it model is a fine-tuned version of Qwen3-VL-8B-Instruct, tailored for Abliterated Captioning / Uncensored Image Captioning. This variant is designed to generate highly detailed and descriptive captions across a broad range of visual categories, including images with complex, sensitive, or nuanced content—across varying aspect ratios and resolutions.
|
| 23 |
+
|
| 24 |
+
## Model Files
|
| 25 |
+
|
| 26 |
+
| File Name | Quant Type | File Size |
|
| 27 |
+
| - | - | - |
|
| 28 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.f16.gguf | F16 | 16.4 GB |
|
| 29 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q2_K.gguf | Q2_K | 3.28 GB |
|
| 30 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q3_K_L.gguf | Q3_K_L | 4.43 GB |
|
| 31 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q3_K_M.gguf | Q3_K_M | 4.12 GB |
|
| 32 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q3_K_S.gguf | Q3_K_S | 3.77 GB |
|
| 33 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q4_K_M.gguf | Q4_K_M | 5.03 GB |
|
| 34 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q4_K_S.gguf | Q4_K_S | 4.8 GB |
|
| 35 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q5_K_M.gguf | Q5_K_M | 5.85 GB |
|
| 36 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q5_K_S.gguf | Q5_K_S | 5.72 GB |
|
| 37 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q6_K.gguf | Q6_K | 6.73 GB |
|
| 38 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.Q8_0.gguf | Q8_0 | 8.71 GB |
|
| 39 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.IQ4_XS.gguf | IQ4_XS | 4.59 GB |
|
| 40 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ1_M.gguf | i1-IQ1_M | 2.26 GB |
|
| 41 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ1_S.gguf | i1-IQ1_S | 2.12 GB |
|
| 42 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ2_M.gguf | i1-IQ2_M | 3.05 GB |
|
| 43 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ2_S.gguf | i1-IQ2_S | 2.86 GB |
|
| 44 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ2_XS.gguf | i1-IQ2_XS | 2.7 GB |
|
| 45 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ2_XXS.gguf | i1-IQ2_XXS | 2.49 GB |
|
| 46 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ3_M.gguf | i1-IQ3_M | 3.9 GB |
|
| 47 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ3_S.gguf | i1-IQ3_S | 3.79 GB |
|
| 48 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ3_XS.gguf | i1-IQ3_XS | 3.63 GB |
|
| 49 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ3_XXS.gguf | i1-IQ3_XXS | 3.37 GB |
|
| 50 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ4_NL.gguf | i1-IQ4_NL | 4.79 GB |
|
| 51 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-IQ4_XS.gguf | i1-IQ4_XS | 4.56 GB |
|
| 52 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q2_K.gguf | i1-Q2_K | 3.28 GB |
|
| 53 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q2_K_S.gguf | i1-Q2_K_S | 3.08 GB |
|
| 54 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q3_K_L.gguf | i1-Q3_K_L | 4.43 GB |
|
| 55 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q3_K_M.gguf | i1-Q3_K_M | 4.12 GB |
|
| 56 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q3_K_S.gguf | i1-Q3_K_S | 3.77 GB |
|
| 57 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q4_0.gguf | i1-Q4_0 | 4.79 GB |
|
| 58 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q4_1.gguf | i1-Q4_1 | 5.25 GB |
|
| 59 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q4_K_M.gguf | i1-Q4_K_M | 5.03 GB |
|
| 60 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q4_K_S.gguf | i1-Q4_K_S | 4.8 GB |
|
| 61 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q5_K_M.gguf | i1-Q5_K_M | 5.85 GB |
|
| 62 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q5_K_S.gguf | i1-Q5_K_S | 5.72 GB |
|
| 63 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.i1-Q6_K.gguf | i1-Q6_K | 6.73 GB |
|
| 64 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.imatrix.gguf | imatrix | 5.35 MB |
|
| 65 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.mmproj-Q8_0.gguf | mmproj-Q8_0 | 752 MB |
|
| 66 |
+
| Qwen3-VL-8B-Abliterated-Caption-it.mmproj-f16.gguf | mmproj-f16 | 1.16 GB |
|
| 67 |
+
|
| 68 |
+
## Quants Usage
|
| 69 |
+
|
| 70 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 71 |
+
|
| 72 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 73 |
+
types (lower is better):
|
| 74 |
+
|
| 75 |
+
|