Hugging Face's logo

tensorblock
/
suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF

GGUF
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
e9925f1
·
verified ·
1 Parent(s): 9f7bb2b

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +78 -0
  3. suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf +3 -0
  4. suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_L.gguf +3 -0
  5. suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_M.gguf +3 -0
  6. suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_S.gguf +3 -0
  7. suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_0.gguf +3 -0
  8. suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_M.gguf +3 -0
  9. suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_S.gguf +3 -0
  10. suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_0.gguf +3 -0
  11. suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M.gguf +3 -0
  12. suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_S.gguf +3 -0
  13. suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K.gguf +3 -0
  14. suzume-llama-3-8B-multilingual-orpo-borda-half-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
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ suzume-llama-3-8B-multilingual-orpo-borda-half-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ - TensorBlock
6
+ - GGUF
7
+ base_model: lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half
8
+ model-index:
9
+ - name: workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_half_borda
10
+ results: []
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ 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>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half - GGUF
25
+
26
+ This repo contains GGUF format model files for [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half).
27
+
28
+ 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).
29
+
30
+ ## Prompt template
31
+
32
+ ```
33
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
34
+
35
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
36
+
37
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
46
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
47
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_L.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
48
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
50
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
51
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
53
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
54
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
55
+ | [suzume-llama-3-8B-multilingual-orpo-borda-half-Q8_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF/tree/main/suzume-llama-3-8B-multilingual-orpo-borda-half-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF --include "suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/suzume-llama-3-8B-multilingual-orpo-borda-half-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```
suzume-llama-3-8B-multilingual-orpo-borda-half-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8597c6d25e6cd25b7470deb5abe30d1a9c94d4782e992adfe05ecb0784bca75c
3
+ size 3179131808
suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d33cb37c6a9eed79980915dcff6880ca61f7311d177b504b77fa02d7f5fb10d
3
+ size 4321956768
suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9fcc6e123878a7120248faf9ed478b5dcdc96568277cc2ef83671fe263657cc
3
+ size 4018918304
suzume-llama-3-8B-multilingual-orpo-borda-half-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6140b3c50c32a544764bc5332285268139c851dcda4e3dcb7d5633eac21155e5
3
+ size 3664499616
suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056c2a84896329b68cfb19bc62ac830cc6546ae4f0e364ff8ae1620e31bdc64f
3
+ size 4661212064
suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2000553f2289abff281bdd9352c3a409dd722159d27536c77b16f4c2c4343a
3
+ size 4920734624
suzume-llama-3-8B-multilingual-orpo-borda-half-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b780b58fdac14e8900b6d8ab0fa1de442e2f6f9e239e579fc7787a79e27554d
3
+ size 4692669344
suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d893d42bff41fcb58cb33687d1bfca6699e5371d0760eb734082031a4606a4
3
+ size 5599294368
suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090d4471c1e318f05ba9fe6c0a674cd5988150097dda14719285d4a33788d34e
3
+ size 5732987808
suzume-llama-3-8B-multilingual-orpo-borda-half-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba10b02d6562791f302b4c7f905dcff18d3e0640daafd3728f821a3d2a541d0
3
+ size 5599294368
suzume-llama-3-8B-multilingual-orpo-borda-half-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8354dad9a844db5ce692c6cc3d92c2c52f23fdefb17000c6025da7d648297a
3
+ size 6596006816
suzume-llama-3-8B-multilingual-orpo-borda-half-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91038554bec6013d15b376eddc65a17f9ea24742c071c4d5dcbaa584c1e44541
3
+ size 8540771232