morriszms commited on
Commit
bab08dd
·
verified ·
1 Parent(s): 8637f3c

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
+ helium-1-2b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ helium-1-2b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ helium-1-2b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ helium-1-2b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ helium-1-2b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ helium-1-2b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ helium-1-2b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ helium-1-2b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ helium-1-2b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ helium-1-2b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ helium-1-2b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ helium-1-2b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-sa-4.0
4
+ language:
5
+ - bg
6
+ - cs
7
+ - da
8
+ - de
9
+ - el
10
+ - en
11
+ - es
12
+ - et
13
+ - fi
14
+ - fr
15
+ - ga
16
+ - hr
17
+ - hu
18
+ - it
19
+ - lt
20
+ - lv
21
+ - mt
22
+ - nl
23
+ - pl
24
+ - pt
25
+ - ro
26
+ - sk
27
+ - sl
28
+ - sv
29
+ pipeline_tag: text-generation
30
+ base_model: kyutai/helium-1-2b
31
+ tags:
32
+ - TensorBlock
33
+ - GGUF
34
+ ---
35
+
36
+ <div style="width: auto; margin-left: auto; margin-right: auto">
37
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
38
+ </div>
39
+
40
+ [![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
41
+ [![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
42
+ [![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
43
+ [![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
44
+ [![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)
45
+
46
+
47
+ ## kyutai/helium-1-2b - GGUF
48
+
49
+ <div style="text-align: left; margin: 20px 0;">
50
+ <a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
51
+ Join our Discord to learn more about what we're building ↗
52
+ </a>
53
+ </div>
54
+
55
+ This repo contains GGUF format model files for [kyutai/helium-1-2b](https://huggingface.co/kyutai/helium-1-2b).
56
+
57
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
58
+
59
+ ## Our projects
60
+ <table border="1" cellspacing="0" cellpadding="10">
61
+ <tr>
62
+ <th colspan="2" style="font-size: 25px;">Forge</th>
63
+ </tr>
64
+ <tr>
65
+ <th colspan="2">
66
+ <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
67
+ </th>
68
+ </tr>
69
+ <tr>
70
+ <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
71
+ </tr>
72
+ <tr>
73
+ <th colspan="2">
74
+ <a href="https://github.com/TensorBlock/forge" target="_blank" style="
75
+ display: inline-block;
76
+ padding: 8px 16px;
77
+ background-color: #FF7F50;
78
+ color: white;
79
+ text-decoration: none;
80
+ border-radius: 6px;
81
+ font-weight: bold;
82
+ font-family: sans-serif;
83
+ ">🚀 Try it now! 🚀</a>
84
+ </th>
85
+ </tr>
86
+
87
+ <tr>
88
+ <th style="font-size: 25px;">Awesome MCP Servers</th>
89
+ <th style="font-size: 25px;">TensorBlock Studio</th>
90
+ </tr>
91
+ <tr>
92
+ <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
93
+ <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
94
+ </tr>
95
+ <tr>
96
+ <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
97
+ <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
98
+ </tr>
99
+ <tr>
100
+ <th>
101
+ <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
102
+ display: inline-block;
103
+ padding: 8px 16px;
104
+ background-color: #FF7F50;
105
+ color: white;
106
+ text-decoration: none;
107
+ border-radius: 6px;
108
+ font-weight: bold;
109
+ font-family: sans-serif;
110
+ ">👀 See what we built 👀</a>
111
+ </th>
112
+ <th>
113
+ <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
114
+ display: inline-block;
115
+ padding: 8px 16px;
116
+ background-color: #FF7F50;
117
+ color: white;
118
+ text-decoration: none;
119
+ border-radius: 6px;
120
+ font-weight: bold;
121
+ font-family: sans-serif;
122
+ ">👀 See what we built 👀</a>
123
+ </th>
124
+ </tr>
125
+ </table>
126
+
127
+ ## Prompt template
128
+
129
+ ```
130
+ Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
131
+ ```
132
+
133
+ ## Model file specification
134
+
135
+ | Filename | Quant type | File Size | Description |
136
+ | -------- | ---------- | --------- | ----------- |
137
+ | [helium-1-2b-Q2_K.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q2_K.gguf) | Q2_K | 0.796 GB | smallest, significant quality loss - not recommended for most purposes |
138
+ | [helium-1-2b-Q3_K_S.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q3_K_S.gguf) | Q3_K_S | 0.923 GB | very small, high quality loss |
139
+ | [helium-1-2b-Q3_K_M.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q3_K_M.gguf) | Q3_K_M | 1.011 GB | very small, high quality loss |
140
+ | [helium-1-2b-Q3_K_L.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q3_K_L.gguf) | Q3_K_L | 1.089 GB | small, substantial quality loss |
141
+ | [helium-1-2b-Q4_0.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q4_0.gguf) | Q4_0 | 1.174 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
142
+ | [helium-1-2b-Q4_K_S.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q4_K_S.gguf) | Q4_K_S | 1.182 GB | small, greater quality loss |
143
+ | [helium-1-2b-Q4_K_M.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q4_K_M.gguf) | Q4_K_M | 1.242 GB | medium, balanced quality - recommended |
144
+ | [helium-1-2b-Q5_0.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q5_0.gguf) | Q5_0 | 1.411 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
145
+ | [helium-1-2b-Q5_K_S.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q5_K_S.gguf) | Q5_K_S | 1.411 GB | large, low quality loss - recommended |
146
+ | [helium-1-2b-Q5_K_M.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q5_K_M.gguf) | Q5_K_M | 1.446 GB | large, very low quality loss - recommended |
147
+ | [helium-1-2b-Q6_K.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q6_K.gguf) | Q6_K | 1.662 GB | very large, extremely low quality loss |
148
+ | [helium-1-2b-Q8_0.gguf](https://huggingface.co/tensorblock/kyutai_helium-1-2b-GGUF/blob/main/helium-1-2b-Q8_0.gguf) | Q8_0 | 2.152 GB | very large, extremely low quality loss - not recommended |
149
+
150
+
151
+ ## Downloading instruction
152
+
153
+ ### Command line
154
+
155
+ Firstly, install Huggingface Client
156
+
157
+ ```shell
158
+ pip install -U "huggingface_hub[cli]"
159
+ ```
160
+
161
+ Then, downoad the individual model file the a local directory
162
+
163
+ ```shell
164
+ huggingface-cli download tensorblock/kyutai_helium-1-2b-GGUF --include "helium-1-2b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
165
+ ```
166
+
167
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
168
+
169
+ ```shell
170
+ huggingface-cli download tensorblock/kyutai_helium-1-2b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
171
+ ```
helium-1-2b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef3402bba5c1033d0e8334114419981efce30528a7162e2044cb4f5ea012a3a
3
+ size 796224000
helium-1-2b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab780f99d3f2753f59896d995a7f2518c1849f6f38022bea0296e34065123236
3
+ size 1089374720
helium-1-2b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aeb2bdbf392ef27e66affe903f59b07f3e4a80585fc4b1a7c6562873cd3facf
3
+ size 1011255808
helium-1-2b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab5deeff7cf3f5372de148e29b9fa6c3503bd61effad4f6703463b77b7449d30
3
+ size 922847744
helium-1-2b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c12dbccfe929c08c3a45e8e973857ba6d995101f98990c89ab15c34755f28cd
3
+ size 1174219264
helium-1-2b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210274f7732d30f7304aa690d48f0c41e18fa92d2aa20bf6f3be4a7bfcb21a10
3
+ size 1242343936
helium-1-2b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42ecbf5191ed1e9eb8fd33899382a294627195aedef0c4583eac321803da1f0
3
+ size 1181559296
helium-1-2b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ddd1eb1fa289cb6b6dd237ae9e949c2da787fa2f1e4611654cbbc6c4437d562
3
+ size 1410804224
helium-1-2b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173435895f3cdcaaccbff2ac91eb44e21765f53c86334231bab189790aed02ef
3
+ size 1445898752
helium-1-2b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05fdb28691eb585eccee6e1f3fdd0bec0562d6fad15eca485cbbbfddc49a916
3
+ size 1410804224
helium-1-2b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a77f0321fc20a49e851e1df71fe325a1ca24bea6ff837ae56187c7142448285
3
+ size 1662175744
helium-1-2b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d53d05cdae4031ee8c704f07bbae32bacc06087ff995ca646a73df13cde591e
3
+ size 2152303104