morriszms commited on
Commit
24806e8
·
verified ·
1 Parent(s): 2e489ad

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
+ Aira-2-774M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Aira-2-774M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Aira-2-774M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Aira-2-774M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Aira-2-774M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Aira-2-774M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Aira-2-774M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Aira-2-774M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Aira-2-774M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Aira-2-774M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Aira-2-774M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Aira-2-774M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Aira-2-774M-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47fc382f13ad4471c3057119f87bcef4207097a0741910f9363c7bf0a441fbb
3
+ size 345520064
Aira-2-774M-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a93fea8ec2d645c94dd77baa53b6a16b8016b36541b7b83759af45a433b9530
3
+ size 493519584
Aira-2-774M-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40600f2bf1333619b8f5525c0816f067fd12b99bae7b4f345848747614ab3e6
3
+ size 458293984
Aira-2-774M-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cfbaab3ee8caa3da8e040b43f33793577d31a15998caafdd1c7b3de32b53a4
3
+ size 393986784
Aira-2-774M-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc00417168919003e5f57c9b49ab33b6705492d652a864675508f811294bba5
3
+ size 496534368
Aira-2-774M-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50213cb27947d113537715fccd0d9c6f0d8753f1e23a4fab72c2b7ce376c3ff
3
+ size 549065568
Aira-2-774M-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a757f3c7fb28e3314c48bdddc35e21bf1f17c2c3c696a0f177410fc2dcf0e65
3
+ size 499811168
Aira-2-774M-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd14785f017b7258aa634aa4ac9480c7a66b8ca7a32c0ac081c4ba44179cbc5
3
+ size 593049728
Aira-2-774M-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273c7bb325cd8f878d96b24287a0c92f41b05b5bcdaed3072a7a03867a76ee5b
3
+ size 632217728
Aira-2-774M-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe8c9fd98ef04c234fc5d35e0ebd635bdd9bf24bf67ed181f75cdf1273ec494
3
+ size 593049728
Aira-2-774M-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f36ffc6d092f6e7e04bc15026fa930acf20d3383e8e44e51c53666d876658c1
3
+ size 695597312
Aira-2-774M-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8d0eb76842b4ea9c4dca277010972358804fb40c24bbd916ddd398207ffcaa
3
+ size 898176704
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - nicholasKluge/instruct-aira-dataset
5
+ language:
6
+ - en
7
+ metrics:
8
+ - accuracy
9
+ library_name: transformers
10
+ tags:
11
+ - alignment
12
+ - instruction tuned
13
+ - text generation
14
+ - conversation
15
+ - assistant
16
+ - TensorBlock
17
+ - GGUF
18
+ pipeline_tag: text-generation
19
+ widget:
20
+ - text: <|startofinstruction|>Can you explain what is Machine Learning?<|endofinstruction|>
21
+ example_title: Machine Learning
22
+ - text: <|startofinstruction|>Do you know anything about virtue ethics?<|endofinstruction|>
23
+ example_title: Ethics
24
+ - text: <|startofinstruction|>How can I make my girlfriend happy?<|endofinstruction|>
25
+ example_title: Advise
26
+ inference:
27
+ parameters:
28
+ repetition_penalty: 1.2
29
+ temperature: 0.2
30
+ top_k: 30
31
+ top_p: 0.3
32
+ max_new_tokens: 200
33
+ length_penalty: 0.3
34
+ early_stopping: true
35
+ co2_eq_emissions:
36
+ emissions: 770
37
+ source: CodeCarbon
38
+ training_type: fine-tuning
39
+ geographical_location: United States of America
40
+ hardware_used: NVIDIA A100-SXM4-40GB
41
+ base_model: nicholasKluge/Aira-2-774M
42
+ ---
43
+
44
+ <div style="width: auto; margin-left: auto; margin-right: auto">
45
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
46
+ </div>
47
+ <div style="display: flex; justify-content: space-between; width: 100%;">
48
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
49
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
50
+ 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>
51
+ </p>
52
+ </div>
53
+ </div>
54
+
55
+ ## nicholasKluge/Aira-2-774M - GGUF
56
+
57
+ This repo contains GGUF format model files for [nicholasKluge/Aira-2-774M](https://huggingface.co/nicholasKluge/Aira-2-774M).
58
+
59
+ 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).
60
+
61
+ <div style="text-align: left; margin: 20px 0;">
62
+ <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;">
63
+ Run them on the TensorBlock client using your local machine ↗
64
+ </a>
65
+ </div>
66
+
67
+ ## Prompt template
68
+
69
+ ```
70
+
71
+ ```
72
+
73
+ ## Model file specification
74
+
75
+ | Filename | Quant type | File Size | Description |
76
+ | -------- | ---------- | --------- | ----------- |
77
+ | [Aira-2-774M-Q2_K.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q2_K.gguf) | Q2_K | 0.322 GB | smallest, significant quality loss - not recommended for most purposes |
78
+ | [Aira-2-774M-Q3_K_S.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q3_K_S.gguf) | Q3_K_S | 0.367 GB | very small, high quality loss |
79
+ | [Aira-2-774M-Q3_K_M.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q3_K_M.gguf) | Q3_K_M | 0.427 GB | very small, high quality loss |
80
+ | [Aira-2-774M-Q3_K_L.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q3_K_L.gguf) | Q3_K_L | 0.460 GB | small, substantial quality loss |
81
+ | [Aira-2-774M-Q4_0.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q4_0.gguf) | Q4_0 | 0.462 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
82
+ | [Aira-2-774M-Q4_K_S.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q4_K_S.gguf) | Q4_K_S | 0.465 GB | small, greater quality loss |
83
+ | [Aira-2-774M-Q4_K_M.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q4_K_M.gguf) | Q4_K_M | 0.511 GB | medium, balanced quality - recommended |
84
+ | [Aira-2-774M-Q5_0.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q5_0.gguf) | Q5_0 | 0.552 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
85
+ | [Aira-2-774M-Q5_K_S.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q5_K_S.gguf) | Q5_K_S | 0.552 GB | large, low quality loss - recommended |
86
+ | [Aira-2-774M-Q5_K_M.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q5_K_M.gguf) | Q5_K_M | 0.589 GB | large, very low quality loss - recommended |
87
+ | [Aira-2-774M-Q6_K.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q6_K.gguf) | Q6_K | 0.648 GB | very large, extremely low quality loss |
88
+ | [Aira-2-774M-Q8_0.gguf](https://huggingface.co/tensorblock/Aira-2-774M-GGUF/blob/main/Aira-2-774M-Q8_0.gguf) | Q8_0 | 0.836 GB | very large, extremely low quality loss - not recommended |
89
+
90
+
91
+ ## Downloading instruction
92
+
93
+ ### Command line
94
+
95
+ Firstly, install Huggingface Client
96
+
97
+ ```shell
98
+ pip install -U "huggingface_hub[cli]"
99
+ ```
100
+
101
+ Then, downoad the individual model file the a local directory
102
+
103
+ ```shell
104
+ huggingface-cli download tensorblock/Aira-2-774M-GGUF --include "Aira-2-774M-Q2_K.gguf" --local-dir MY_LOCAL_DIR
105
+ ```
106
+
107
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
108
+
109
+ ```shell
110
+ huggingface-cli download tensorblock/Aira-2-774M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
111
+ ```