morriszms commited on
Commit
6029e31
1 Parent(s): ff24a98

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-pre2-ins1-lora3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ llama3-pre1-pre2-ins1-lora3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama3-pre1-pre2-ins1-lora3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ llama3-pre1-pre2-ins1-lora3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ llama3-pre1-pre2-ins1-lora3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ llama3-pre1-pre2-ins1-lora3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ llama3-pre1-pre2-ins1-lora3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ llama3-pre1-pre2-ins1-lora3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ llama3-pre1-pre2-ins1-lora3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ llama3-pre1-pre2-ins1-lora3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ llama3-pre1-pre2-ins1-lora3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ llama3-pre1-pre2-ins1-lora3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - en
5
+ - ko
6
+ pipeline_tag: translation
7
+ license: mit
8
+ datasets:
9
+ - pre
10
+ base_model: 4yo1/llama3-pre1-pre2-ins1-lora3
11
+ tags:
12
+ - TensorBlock
13
+ - GGUF
14
+ ---
15
+
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <div style="display: flex; justify-content: space-between; width: 100%;">
20
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
22
+ 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>
23
+ </p>
24
+ </div>
25
+ </div>
26
+
27
+ ## 4yo1/llama3-pre1-pre2-ins1-lora3 - GGUF
28
+
29
+ This repo contains GGUF format model files for [4yo1/llama3-pre1-pre2-ins1-lora3](https://huggingface.co/4yo1/llama3-pre1-pre2-ins1-lora3).
30
+
31
+ 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).
32
+
33
+ ## Prompt template
34
+
35
+ ```
36
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
37
+
38
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
39
+
40
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
41
+ ```
42
+
43
+ ## Model file specification
44
+
45
+ | Filename | Quant type | File Size | Description |
46
+ | -------- | ---------- | --------- | ----------- |
47
+ | [llama3-pre1-pre2-ins1-lora3-Q2_K.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q2_K.gguf) | Q2_K | 3.055 GB | smallest, significant quality loss - not recommended for most purposes |
48
+ | [llama3-pre1-pre2-ins1-lora3-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q3_K_S.gguf) | Q3_K_S | 3.515 GB | very small, high quality loss |
49
+ | [llama3-pre1-pre2-ins1-lora3-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q3_K_M.gguf) | Q3_K_M | 3.845 GB | very small, high quality loss |
50
+ | [llama3-pre1-pre2-ins1-lora3-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q3_K_L.gguf) | Q3_K_L | 4.127 GB | small, substantial quality loss |
51
+ | [llama3-pre1-pre2-ins1-lora3-Q4_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q4_0.gguf) | Q4_0 | 4.454 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
52
+ | [llama3-pre1-pre2-ins1-lora3-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q4_K_S.gguf) | Q4_K_S | 4.483 GB | small, greater quality loss |
53
+ | [llama3-pre1-pre2-ins1-lora3-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q4_K_M.gguf) | Q4_K_M | 4.696 GB | medium, balanced quality - recommended |
54
+ | [llama3-pre1-pre2-ins1-lora3-Q5_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q5_0.gguf) | Q5_0 | 5.338 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
55
+ | [llama3-pre1-pre2-ins1-lora3-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q5_K_S.gguf) | Q5_K_S | 5.338 GB | large, low quality loss - recommended |
56
+ | [llama3-pre1-pre2-ins1-lora3-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q5_K_M.gguf) | Q5_K_M | 5.462 GB | large, very low quality loss - recommended |
57
+ | [llama3-pre1-pre2-ins1-lora3-Q6_K.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q6_K.gguf) | Q6_K | 6.277 GB | very large, extremely low quality loss |
58
+ | [llama3-pre1-pre2-ins1-lora3-Q8_0.gguf](https://huggingface.co/tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF/tree/main/llama3-pre1-pre2-ins1-lora3-Q8_0.gguf) | Q8_0 | 8.127 GB | very large, extremely low quality loss - not recommended |
59
+
60
+
61
+ ## Downloading instruction
62
+
63
+ ### Command line
64
+
65
+ Firstly, install Huggingface Client
66
+
67
+ ```shell
68
+ pip install -U "huggingface_hub[cli]"
69
+ ```
70
+
71
+ Then, downoad the individual model file the a local directory
72
+
73
+ ```shell
74
+ huggingface-cli download tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF --include "llama3-pre1-pre2-ins1-lora3-Q2_K.gguf" --local-dir MY_LOCAL_DIR
75
+ ```
76
+
77
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/llama3-pre1-pre2-ins1-lora3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
81
+ ```
llama3-pre1-pre2-ins1-lora3-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81896bbde484f23fe857f9c6e230cfe3e8aac48c6e13f458a6f2a992e1a3daaa
3
+ size 3280085952
llama3-pre1-pre2-ins1-lora3-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b97e6222aa4b533210d8389096bc356dd596051e8da857a28ee5e5d8eb5c16
3
+ size 4431733856
llama3-pre1-pre2-ins1-lora3-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1026d0ce110bc0f426d9b0a31a2f58c7f75ceb5dd0e83f53a6cda9cccec52a
3
+ size 4128695392
llama3-pre1-pre2-ins1-lora3-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c4c0d53969b187c8c8f2fc610a8f742262f5894d8b32e4ea352da88260804e
3
+ size 3774276704
llama3-pre1-pre2-ins1-lora3-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd7ba17b17f25c0d7d05bdc6c92e0320ed35354b41865eed79d08a3420de505
3
+ size 4782526848
llama3-pre1-pre2-ins1-lora3-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80496307771770876f46292a588c17db6e6147ab76f0087ad3d6890717b0c2e6
3
+ size 5042049408
llama3-pre1-pre2-ins1-lora3-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c507a259e6c896f27f74552af08eb2b0b36128f6502e1cd73b6e67d7c516c252
3
+ size 4813984128
llama3-pre1-pre2-ins1-lora3-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845e3acfd2e6f5d1f2d3cb25e7df3a744ad60dd20eae1b44be8a27f2a5ae222e
3
+ size 5731468160
llama3-pre1-pre2-ins1-lora3-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b41a0879ce4322c81cf5a773b44df10bf0bea07e0f473cdd58716ae4bd57591
3
+ size 5865161600
llama3-pre1-pre2-ins1-lora3-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ad72893d5e3dc63c3811a395194ca00603354cb757058b5355c816f5410895
3
+ size 5731468160
llama3-pre1-pre2-ins1-lora3-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8299a40f450e6b4b8e4ed0533f2f95e1750d00731ef61f1f9a2d5ed831d6a57a
3
+ size 6739718304
llama3-pre1-pre2-ins1-lora3-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e308c1a4946906ccdb3609ed6007e64f390e11ecead22efc1a939a069bade3fc
3
+ size 8726561376