Hugging Face's logo

tensorblock
/
llama3-8B-dpo-sft-v1-GGUF

Transformers
GGUF
llama-factory
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
857c5ff
·
verified ·
1 Parent(s): ea71988

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +80 -0
  3. llama3-8B-dpo-sft-v1-Q2_K.gguf +3 -0
  4. llama3-8B-dpo-sft-v1-Q3_K_L.gguf +3 -0
  5. llama3-8B-dpo-sft-v1-Q3_K_M.gguf +3 -0
  6. llama3-8B-dpo-sft-v1-Q3_K_S.gguf +3 -0
  7. llama3-8B-dpo-sft-v1-Q4_0.gguf +3 -0
  8. llama3-8B-dpo-sft-v1-Q4_K_M.gguf +3 -0
  9. llama3-8B-dpo-sft-v1-Q4_K_S.gguf +3 -0
  10. llama3-8B-dpo-sft-v1-Q5_0.gguf +3 -0
  11. llama3-8B-dpo-sft-v1-Q5_K_M.gguf +3 -0
  12. llama3-8B-dpo-sft-v1-Q5_K_S.gguf +3 -0
  13. llama3-8B-dpo-sft-v1-Q6_K.gguf +3 -0
  14. llama3-8B-dpo-sft-v1-Q8_0.gguf +3 -0
.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
+ llama3-8B-dpo-sft-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ llama3-8B-dpo-sft-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama3-8B-dpo-sft-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ llama3-8B-dpo-sft-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ llama3-8B-dpo-sft-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ llama3-8B-dpo-sft-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ llama3-8B-dpo-sft-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ llama3-8B-dpo-sft-v1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ llama3-8B-dpo-sft-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ llama3-8B-dpo-sft-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ llama3-8B-dpo-sft-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ llama3-8B-dpo-sft-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - llama-factory
5
+ - TensorBlock
6
+ - GGUF
7
+ license: apache-2.0
8
+ base_model: youjunhyeok/llama3-8B-dpo-sft-v1
9
+ ---
10
+
11
+ <div style="width: auto; margin-left: auto; margin-right: auto">
12
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
+ </div>
14
+ <div style="display: flex; justify-content: space-between; width: 100%;">
15
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
16
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
17
+ 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>
18
+ </p>
19
+ </div>
20
+ </div>
21
+
22
+ ## youjunhyeok/llama3-8B-dpo-sft-v1 - GGUF
23
+
24
+ This repo contains GGUF format model files for [youjunhyeok/llama3-8B-dpo-sft-v1](https://huggingface.co/youjunhyeok/llama3-8B-dpo-sft-v1).
25
+
26
+ 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).
27
+
28
+ <div style="text-align: left; margin: 20px 0;">
29
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
30
+ Run them on the TensorBlock client using your local machine ↗
31
+ </a>
32
+ </div>
33
+
34
+ ## Prompt template
35
+
36
+ ```
37
+ {system_prompt}
38
+ Human: {prompt}
39
+ Assistant:
40
+ ```
41
+
42
+ ## Model file specification
43
+
44
+ | Filename | Quant type | File Size | Description |
45
+ | -------- | ---------- | --------- | ----------- |
46
+ | [llama3-8B-dpo-sft-v1-Q2_K.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
47
+ | [llama3-8B-dpo-sft-v1-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
48
+ | [llama3-8B-dpo-sft-v1-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
49
+ | [llama3-8B-dpo-sft-v1-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
50
+ | [llama3-8B-dpo-sft-v1-Q4_0.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
+ | [llama3-8B-dpo-sft-v1-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
52
+ | [llama3-8B-dpo-sft-v1-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
53
+ | [llama3-8B-dpo-sft-v1-Q5_0.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
+ | [llama3-8B-dpo-sft-v1-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
55
+ | [llama3-8B-dpo-sft-v1-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
56
+ | [llama3-8B-dpo-sft-v1-Q6_K.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
57
+ | [llama3-8B-dpo-sft-v1-Q8_0.gguf](https://huggingface.co/tensorblock/llama3-8B-dpo-sft-v1-GGUF/blob/main/llama3-8B-dpo-sft-v1-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
58
+
59
+
60
+ ## Downloading instruction
61
+
62
+ ### Command line
63
+
64
+ Firstly, install Huggingface Client
65
+
66
+ ```shell
67
+ pip install -U "huggingface_hub[cli]"
68
+ ```
69
+
70
+ Then, downoad the individual model file the a local directory
71
+
72
+ ```shell
73
+ huggingface-cli download tensorblock/llama3-8B-dpo-sft-v1-GGUF --include "llama3-8B-dpo-sft-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
74
+ ```
75
+
76
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
77
+
78
+ ```shell
79
+ huggingface-cli download tensorblock/llama3-8B-dpo-sft-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
80
+ ```
llama3-8B-dpo-sft-v1-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db60980f9d90cce9df79ca63a25f148e52483650a741fff5f276aa5057d4679
3
+ size 3179131552
llama3-8B-dpo-sft-v1-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d10c9227486e70e84a9a39466ee963bbca2cdcfc9cf4ff0b9661447a4910c8e
3
+ size 4321956512
llama3-8B-dpo-sft-v1-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8e67fdf511b87766246f352bd6453fee6545c4fc9a1fdf5c6d5b713d8760e1
3
+ size 4018918048
llama3-8B-dpo-sft-v1-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95931701777238d90b2c405a39a0cef5b4a3866863451e2c8ed83115935f852b
3
+ size 3664499360
llama3-8B-dpo-sft-v1-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb478db741628af70bb296a3aa13c18eb6d79ba5de69eac852fcf1503fee786
3
+ size 4661211808
llama3-8B-dpo-sft-v1-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af46baf0da7c3c2196e6ab9dd71aabf339b12ce223209a56250502e3b36126d
3
+ size 4920734368
llama3-8B-dpo-sft-v1-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4282411bc1f3126f5716f702c9fd15ba9646df5e24ac20d11c807bdaf799e1
3
+ size 4692669088
llama3-8B-dpo-sft-v1-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16c2fe39943ec6cbcc5918fb6e4d17158cb4d465fa88e98bb6f71e996f7ba54
3
+ size 5599294112
llama3-8B-dpo-sft-v1-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add8a921a40ca5c567f051ec300feaf4bdf9886b7a8b77daf61c9408435ec56e
3
+ size 5732987552
llama3-8B-dpo-sft-v1-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2da981c57ba64fe47ba772d98901062fa4268614a17dbe6836bf4e77581d49c
3
+ size 5599294112
llama3-8B-dpo-sft-v1-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ccd6a1a38bea449cca8a92a4e5d931d11ccf294465a6152bc81723e9c07f2e
3
+ size 6596006560
llama3-8B-dpo-sft-v1-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d220abd6d21ba3f1024b2f470db2d6cc71d17308d6e3895a7ba4de2089fe18b0
3
+ size 8540770976