theprint commited on
Commit
d401fd2
·
verified ·
1 Parent(s): 4951684

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ DevilsAdvocate-7B-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ DevilsAdvocate-7B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
38
+ DevilsAdvocate-7B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
39
+ DevilsAdvocate-7B-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
40
+ DevilsAdvocate-7B-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
41
+ DevilsAdvocate-7B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DevilsAdvocate-7B-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e127a2a5fe05faabdb5f849bfb9a7a9bd93f7c8330b1e57b42e1521746f01be
3
+ size 15237853088
DevilsAdvocate-7B-q3_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e646556ea820eb515e7ec0c4c03708837486ae41aab60eda106e6b951888c833
3
+ size 3808391072
DevilsAdvocate-7B-q4_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e795b935c1f9064145accc3360bb1c4189e8bd33ee045d28820987d65ea871
3
+ size 4683073440
DevilsAdvocate-7B-q5_k_m.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57756e466a71c32a8b78109de32fac7fca6e60d5538b2d395b21d64e80d4bc59
3
+ size 5444831136
DevilsAdvocate-7B-q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85306c7618812cc02cce187b7f5ec355d1fea82e7482cb05f8351b5c29b1d23d
3
+ size 6254198688
DevilsAdvocate-7B-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1e1e3393e02e22bcd655e337d3d5ea579dde4db805db92dcbd4e69ef8f68cf
3
+ size 8098525088
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B-Instruct
3
+ library_name: gguf
4
+ pipeline_tag: text-generation
5
+ language: en
6
+ license: mit
7
+ tags:
8
+ - gguf
9
+ - quantized
10
+ - llama.cpp
11
+ - devilsadvocate-7b
12
+ model_type: llama
13
+ quantized_by: theprint
14
+ ---
15
+ # DevilsAdvocate-7B - GGUF Quantized
16
+
17
+ Quantized GGUF versions of [DevilsAdvocate-7B](https://huggingface.co/theprint/DevilsAdvocate-7B) for use with llama.cpp and other GGUF-compatible inference engines.
18
+
19
+ ## Original Model
20
+
21
+ - **Base model:** [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
22
+ - **Fine-tuned model:** [theprint/DevilsAdvocate-7B](https://huggingface.co/theprint/DevilsAdvocate-7B)
23
+ - **Quantized by:** theprint
24
+
25
+ ## Available Quantizations
26
+
27
+ - `DevilsAdvocate-7B-f16.gguf` (14531.9 MB) - 16-bit float (original precision, largest file)
28
+ - `DevilsAdvocate-7B-q3_k_m.gguf` (3632.0 MB) - 3-bit quantization (medium quality)
29
+ - `DevilsAdvocate-7B-q4_k_m.gguf` (4466.1 MB) - 4-bit quantization (medium, recommended for most use cases)
30
+ - `DevilsAdvocate-7B-q5_k_m.gguf` (5192.6 MB) - 5-bit quantization (medium, good quality)
31
+ - `DevilsAdvocate-7B-q6_k.gguf` (5964.5 MB) - 6-bit quantization (high quality)
32
+ - `DevilsAdvocate-7B-q8_0.gguf` (7723.4 MB) - 8-bit quantization (very high quality)
33
+
34
+ ## Usage
35
+
36
+ ### With llama.cpp
37
+
38
+ ```bash
39
+ # Download recommended quantization
40
+ wget https://huggingface.co/theprint/DevilsAdvocate-7B-GGUF/resolve/main/DevilsAdvocate-7B-q4_k_m.gguf
41
+
42
+ # Run inference
43
+ ./llama.cpp/main -m DevilsAdvocate-7B-q4_k_m.gguf \
44
+ -p "Your prompt here" \
45
+ -n 256 \
46
+ --temp 0.7 \
47
+ --top-p 0.9
48
+ ```
49
+
50
+ ### With other GGUF tools
51
+
52
+ These files are compatible with:
53
+ - [llama.cpp](https://github.com/ggerganov/llama.cpp)
54
+ - [Ollama](https://ollama.ai/) (import as custom model)
55
+ - [KoboldCpp](https://github.com/LostRuins/koboldcpp)
56
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
57
+
58
+ ## Quantization Info
59
+
60
+ **Recommended:** `q4_k_m` provides the best balance of size, speed, and quality for most use cases.
61
+
62
+ **For maximum quality:** Use `q8_0` or `f16`
63
+ **For maximum speed/smallest size:** Use `q3_k_m` or `q4_k_s`
64
+
65
+ ## License
66
+
67
+ mit
68
+
69
+ ## Citation
70
+
71
+ ```bibtex
72
+ @misc{devilsadvocate_7b_gguf,
73
+ title={DevilsAdvocate-7B GGUF Quantized Models},
74
+ author={theprint},
75
+ year={2025},
76
+ publisher={Hugging Face},
77
+ url={https://huggingface.co/theprint/DevilsAdvocate-7B-GGUF}
78
+ }
79
+ ```