morriszms commited on
Commit
6e4c43f
·
verified ·
1 Parent(s): 651bf61

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ Llama-3-8B-Instruct-abliterated-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3-8B-Instruct-abliterated-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3-8B-Instruct-abliterated-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3-8B-Instruct-abliterated-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3-8B-Instruct-abliterated-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3-8B-Instruct-abliterated-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3-8B-Instruct-abliterated-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3-8B-Instruct-abliterated-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-3-8B-Instruct-abliterated-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-3-8B-Instruct-abliterated-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-3-8B-Instruct-abliterated-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-3-8B-Instruct-abliterated-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3-8B-Instruct-abliterated-v2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbca012385ca9ebbc1aee3e0f64ace1ce254156511c58524615fbf4c6d9f634
3
+ size 3179131456
Llama-3-8B-Instruct-abliterated-v2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a49529a070e8f951ae2b55cddc89a80e9c57659103f63a0b6bce7a93372544
3
+ size 4321956416
Llama-3-8B-Instruct-abliterated-v2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cede634994ea61219d3bc2409689409dc6890612484ef0eba9645663c0d685e1
3
+ size 4018917952
Llama-3-8B-Instruct-abliterated-v2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61d457a6f7bfa9dd818197b63e664c3de1013a8ea23ffaac9ef8628adbb5b8e
3
+ size 3664499264
Llama-3-8B-Instruct-abliterated-v2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e5153a9fb859a3466b5086a5f22a2915bb8604ce1a7e86470737eb58ceda57
3
+ size 4661211712
Llama-3-8B-Instruct-abliterated-v2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d079f4d51f9607c6c8c8476ca04e62f06bdc5cfb6c9bbf534e4eec7b651d4f8
3
+ size 4920734272
Llama-3-8B-Instruct-abliterated-v2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43cdc9a2379e73a704d43e37796f5509f7c415df31c477e49c43cf5674393cc
3
+ size 4692668992
Llama-3-8B-Instruct-abliterated-v2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b929607adc2f8352c51f56662a4eb1a0f78b1b77ca4b926f01fe8a1cb81b7dc3
3
+ size 5599294016
Llama-3-8B-Instruct-abliterated-v2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5aa49274b334699297d8b84a7a6824bec08f8d43fde206a0f4785b8b7259d1
3
+ size 5732987456
Llama-3-8B-Instruct-abliterated-v2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33f6a299c8821e3f90a021bc0699b1afdded8ff223372655f17f99ac68fb5b0
3
+ size 5599294016
Llama-3-8B-Instruct-abliterated-v2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2b89805e1c2751cf01ad7e10811accff85c0e7bc858cc3ec2de353f586eea0
3
+ size 6596006464
Llama-3-8B-Instruct-abliterated-v2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af35644efe9946d7c4270207d4f917c80d926046c50b0b6c109e851fc293bf82
3
+ size 8540770880
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3
4
+ tags:
5
+ - TensorBlock
6
+ - GGUF
7
+ base_model: cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
8
+ ---
9
+
10
+ <div style="width: auto; margin-left: auto; margin-right: auto">
11
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
12
+ </div>
13
+ <div style="display: flex; justify-content: space-between; width: 100%;">
14
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
15
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
16
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
17
+ </p>
18
+ </div>
19
+ </div>
20
+
21
+ ## cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 - GGUF
22
+
23
+ This repo contains GGUF format model files for [cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2](https://huggingface.co/cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2).
24
+
25
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
26
+
27
+ ## Prompt template
28
+
29
+ ```
30
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
31
+
32
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
33
+
34
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
35
+ ```
36
+
37
+ ## Model file specification
38
+
39
+ | Filename | Quant type | File Size | Description |
40
+ | -------- | ---------- | --------- | ----------- |
41
+ | [Llama-3-8B-Instruct-abliterated-v2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
42
+ | [Llama-3-8B-Instruct-abliterated-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
43
+ | [Llama-3-8B-Instruct-abliterated-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
44
+ | [Llama-3-8B-Instruct-abliterated-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
45
+ | [Llama-3-8B-Instruct-abliterated-v2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
46
+ | [Llama-3-8B-Instruct-abliterated-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
47
+ | [Llama-3-8B-Instruct-abliterated-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
48
+ | [Llama-3-8B-Instruct-abliterated-v2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
49
+ | [Llama-3-8B-Instruct-abliterated-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
50
+ | [Llama-3-8B-Instruct-abliterated-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
51
+ | [Llama-3-8B-Instruct-abliterated-v2-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
52
+ | [Llama-3-8B-Instruct-abliterated-v2-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF/tree/main/Llama-3-8B-Instruct-abliterated-v2-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
53
+
54
+
55
+ ## Downloading instruction
56
+
57
+ ### Command line
58
+
59
+ Firstly, install Huggingface Client
60
+
61
+ ```shell
62
+ pip install -U "huggingface_hub[cli]"
63
+ ```
64
+
65
+ Then, downoad the individual model file the a local directory
66
+
67
+ ```shell
68
+ huggingface-cli download tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF --include "Llama-3-8B-Instruct-abliterated-v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
69
+ ```
70
+
71
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
72
+
73
+ ```shell
74
+ huggingface-cli download tensorblock/Llama-3-8B-Instruct-abliterated-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
75
+ ```