Hugging Face's logo

tensorblock
/
raspberry-3B-GGUF

Transformers
GGUF
Generated from Trainer
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
41e5117
·
verified ·
1 Parent(s): 8a29612

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +87 -0
  3. raspberry-3B-Q2_K.gguf +3 -0
  4. raspberry-3B-Q3_K_L.gguf +3 -0
  5. raspberry-3B-Q3_K_M.gguf +3 -0
  6. raspberry-3B-Q3_K_S.gguf +3 -0
  7. raspberry-3B-Q4_0.gguf +3 -0
  8. raspberry-3B-Q4_K_M.gguf +3 -0
  9. raspberry-3B-Q4_K_S.gguf +3 -0
  10. raspberry-3B-Q5_0.gguf +3 -0
  11. raspberry-3B-Q5_K_M.gguf +3 -0
  12. raspberry-3B-Q5_K_S.gguf +3 -0
  13. raspberry-3B-Q6_K.gguf +3 -0
  14. raspberry-3B-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
+ raspberry-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ raspberry-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ raspberry-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ raspberry-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ raspberry-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ raspberry-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ raspberry-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ raspberry-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ raspberry-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ raspberry-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ raspberry-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ raspberry-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: transformers
4
+ tags:
5
+ - generated_from_trainer
6
+ - TensorBlock
7
+ - GGUF
8
+ base_model: arcee-ai/raspberry-3B
9
+ license_name: qwen-research
10
+ license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
11
+ model-index:
12
+ - name: outputs/gelato-3b
13
+ results: []
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
+ ## arcee-ai/raspberry-3B - GGUF
28
+
29
+ This repo contains GGUF format model files for [arcee-ai/raspberry-3B](https://huggingface.co/arcee-ai/raspberry-3B).
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
+ <div style="text-align: left; margin: 20px 0;">
34
+ <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;">
35
+ Run them on the TensorBlock client using your local machine ↗
36
+ </a>
37
+ </div>
38
+
39
+ ## Prompt template
40
+
41
+ ```
42
+ <|im_start|>system
43
+ {system_prompt}<|im_end|>
44
+ <|im_start|>user
45
+ {prompt}<|im_end|>
46
+ <|im_start|>assistant
47
+ ```
48
+
49
+ ## Model file specification
50
+
51
+ | Filename | Quant type | File Size | Description |
52
+ | -------- | ---------- | --------- | ----------- |
53
+ | [raspberry-3B-Q2_K.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q2_K.gguf) | Q2_K | 1.187 GB | smallest, significant quality loss - not recommended for most purposes |
54
+ | [raspberry-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_S.gguf) | Q3_K_S | 1.354 GB | very small, high quality loss |
55
+ | [raspberry-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_M.gguf) | Q3_K_M | 1.481 GB | very small, high quality loss |
56
+ | [raspberry-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q3_K_L.gguf) | Q3_K_L | 1.590 GB | small, substantial quality loss |
57
+ | [raspberry-3B-Q4_0.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_0.gguf) | Q4_0 | 1.698 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
58
+ | [raspberry-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_K_S.gguf) | Q4_K_S | 1.708 GB | small, greater quality loss |
59
+ | [raspberry-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q4_K_M.gguf) | Q4_K_M | 1.797 GB | medium, balanced quality - recommended |
60
+ | [raspberry-3B-Q5_0.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_0.gguf) | Q5_0 | 2.021 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
61
+ | [raspberry-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_K_S.gguf) | Q5_K_S | 2.021 GB | large, low quality loss - recommended |
62
+ | [raspberry-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q5_K_M.gguf) | Q5_K_M | 2.072 GB | large, very low quality loss - recommended |
63
+ | [raspberry-3B-Q6_K.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q6_K.gguf) | Q6_K | 2.364 GB | very large, extremely low quality loss |
64
+ | [raspberry-3B-Q8_0.gguf](https://huggingface.co/tensorblock/raspberry-3B-GGUF/blob/main/raspberry-3B-Q8_0.gguf) | Q8_0 | 3.060 GB | very large, extremely low quality loss - not recommended |
65
+
66
+
67
+ ## Downloading instruction
68
+
69
+ ### Command line
70
+
71
+ Firstly, install Huggingface Client
72
+
73
+ ```shell
74
+ pip install -U "huggingface_hub[cli]"
75
+ ```
76
+
77
+ Then, downoad the individual model file the a local directory
78
+
79
+ ```shell
80
+ huggingface-cli download tensorblock/raspberry-3B-GGUF --include "raspberry-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
81
+ ```
82
+
83
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
84
+
85
+ ```shell
86
+ huggingface-cli download tensorblock/raspberry-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
87
+ ```
raspberry-3B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523686497db85163ec39cfc91f9463b372188add9c0e3052eb38c77ac9605ed5
3
+ size 1274755840
raspberry-3B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce685497397fe32d733adc879959a7b7c64e0bd76a3061531b22edefcf9b475
3
+ size 1707391744
raspberry-3B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47af5f0857e979da7f759d93ffde967941cf0afd34344a4ab70980be659a203
3
+ size 1590475520
raspberry-3B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d67503403e6c7eca1d6655451e3c84f3a2172359c834a5dbc69dd9275302d0d
3
+ size 1454357248
raspberry-3B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1457c388377775143a6991966c876a015db35a39446e6face64c3dbf4af8f2eb
3
+ size 1822849792
raspberry-3B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e248e934f56cb783db9747367820d1335d8e80683f8f1779c4d6b75c4b386b
3
+ size 1929902848
raspberry-3B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623368e507530e7c2066199710d9fbf05dcd2ef92a204ad8af36cfb2ebb76ab7
3
+ size 1834384128
raspberry-3B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f4a4f0a64a3e0c5a910a23861f3342a08098b2dfa37837bdd245486856d508
3
+ size 2169666304
raspberry-3B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1b37ea16fd078aecee12ea02c0c19097adfb381db133768bfa60d7e557fd30
3
+ size 2224814848
raspberry-3B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77773dd75276d6b84b5e9fe7a73103a3848f0eaebe76e4d83c22a5550f6b6624
3
+ size 2169666304
raspberry-3B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9610e725876014bc4af0630b61b625e61a1410352030debc2717ef7db756d022
3
+ size 2538158848
raspberry-3B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5229e4fbcc834cea4ee33b1a7cca29e009326171639529675666178d803bcf67
3
+ size 3285476096