morriszms commited on
Commit
7904992
·
verified ·
1 Parent(s): 36a4257

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
+ llama3-pre1-ds-lora2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ llama3-pre1-ds-lora2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama3-pre1-ds-lora2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ llama3-pre1-ds-lora2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ llama3-pre1-ds-lora2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ llama3-pre1-ds-lora2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ llama3-pre1-ds-lora2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ llama3-pre1-ds-lora2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ llama3-pre1-ds-lora2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ llama3-pre1-ds-lora2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ llama3-pre1-ds-lora2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ llama3-pre1-ds-lora2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - en
5
+ - ko
6
+ pipeline_tag: translation
7
+ tags:
8
+ - llama-3-ko
9
+ - TensorBlock
10
+ - GGUF
11
+ license: mit
12
+ datasets:
13
+ - recipes
14
+ base_model: 4yo1/llama3-pre1-ds-lora2
15
+ ---
16
+
17
+ <div style="width: auto; margin-left: auto; margin-right: auto">
18
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </div>
20
+ <div style="display: flex; justify-content: space-between; width: 100%;">
21
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
23
+ 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>
24
+ </p>
25
+ </div>
26
+ </div>
27
+
28
+ ## 4yo1/llama3-pre1-ds-lora2 - GGUF
29
+
30
+ This repo contains GGUF format model files for [4yo1/llama3-pre1-ds-lora2](https://huggingface.co/4yo1/llama3-pre1-ds-lora2).
31
+
32
+ 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).
33
+
34
+ <div style="text-align: left; margin: 20px 0;">
35
+ <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;">
36
+ Run them on the TensorBlock client using your local machine ↗
37
+ </a>
38
+ </div>
39
+
40
+ ## Prompt template
41
+
42
+ ```
43
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
44
+
45
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
46
+
47
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
48
+ ```
49
+
50
+ ## Model file specification
51
+
52
+ | Filename | Quant type | File Size | Description |
53
+ | -------- | ---------- | --------- | ----------- |
54
+ | [llama3-pre1-ds-lora2-Q2_K.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q2_K.gguf) | Q2_K | 3.280 GB | smallest, significant quality loss - not recommended for most purposes |
55
+ | [llama3-pre1-ds-lora2-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q3_K_S.gguf) | Q3_K_S | 3.774 GB | very small, high quality loss |
56
+ | [llama3-pre1-ds-lora2-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q3_K_M.gguf) | Q3_K_M | 4.129 GB | very small, high quality loss |
57
+ | [llama3-pre1-ds-lora2-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q3_K_L.gguf) | Q3_K_L | 4.432 GB | small, substantial quality loss |
58
+ | [llama3-pre1-ds-lora2-Q4_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q4_0.gguf) | Q4_0 | 4.783 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
59
+ | [llama3-pre1-ds-lora2-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q4_K_S.gguf) | Q4_K_S | 4.814 GB | small, greater quality loss |
60
+ | [llama3-pre1-ds-lora2-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q4_K_M.gguf) | Q4_K_M | 5.042 GB | medium, balanced quality - recommended |
61
+ | [llama3-pre1-ds-lora2-Q5_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q5_0.gguf) | Q5_0 | 5.731 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
62
+ | [llama3-pre1-ds-lora2-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q5_K_S.gguf) | Q5_K_S | 5.731 GB | large, low quality loss - recommended |
63
+ | [llama3-pre1-ds-lora2-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q5_K_M.gguf) | Q5_K_M | 5.865 GB | large, very low quality loss - recommended |
64
+ | [llama3-pre1-ds-lora2-Q6_K.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q6_K.gguf) | Q6_K | 6.740 GB | very large, extremely low quality loss |
65
+ | [llama3-pre1-ds-lora2-Q8_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-ds-lora2-GGUF/blob/main/llama3-pre1-ds-lora2-Q8_0.gguf) | Q8_0 | 8.727 GB | very large, extremely low quality loss - not recommended |
66
+
67
+
68
+ ## Downloading instruction
69
+
70
+ ### Command line
71
+
72
+ Firstly, install Huggingface Client
73
+
74
+ ```shell
75
+ pip install -U "huggingface_hub[cli]"
76
+ ```
77
+
78
+ Then, downoad the individual model file the a local directory
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/llama3-pre1-ds-lora2-GGUF --include "llama3-pre1-ds-lora2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
82
+ ```
83
+
84
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/llama3-pre1-ds-lora2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
88
+ ```
llama3-pre1-ds-lora2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeab5043cb4534d477333b55853e2ef42477644f60d94a3e4405de0914969304
3
+ size 3280085952
llama3-pre1-ds-lora2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759f24929145379c1218a627ba2c23f62d74d954ec004b4bf7ce6efc56f8c80d
3
+ size 4431733856
llama3-pre1-ds-lora2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3654c325d4d2279243b7605104533f79d13fafeb39ac7bacde3ef26bad6b5c06
3
+ size 4128695392
llama3-pre1-ds-lora2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed01f1d1c492173e8572d2223cc2eac906b167a27822793952ce722a81370b11
3
+ size 3774276704
llama3-pre1-ds-lora2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f998665049f7a7bd33d330273d56fd23601e71fe98e7ef2315b9fc323daba8c
3
+ size 4782526848
llama3-pre1-ds-lora2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea3b1f1ffc0966e3b57b0e8b8636756ad3e41991fb18d0e6213b990852ef8f5
3
+ size 5042049408
llama3-pre1-ds-lora2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4475be3009da68fcffd90b9df592fa295c0c609ae1744892d2f410586aae4c2d
3
+ size 4813984128
llama3-pre1-ds-lora2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24b69c1f68a63e83f71511b927ecc558393fa08bc36cfb3e0e4aadd2b9c8869
3
+ size 5731468160
llama3-pre1-ds-lora2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bc10f9b440940736fc0b0952fa926274aa6f9b0af1bcc565c41a45e3cf38fb
3
+ size 5865161600
llama3-pre1-ds-lora2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9442b08c683850c8be05305e4c9c2e2d27dd526023b8348bcca89d88a3594656
3
+ size 5731468160
llama3-pre1-ds-lora2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfe8de2edea4aa2a3815570fc4745c4d2072370565a327333f46c3033cc80df
3
+ size 6739718304
llama3-pre1-ds-lora2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01942abc90dd6bfc474d87f8b4e14b95677fa40d00d2ebd229be4104bbaaa2db
3
+ size 8726561376