Skip to content

Commit 4547283

Browse files
manyosomanyoso
authored
Add Llama 3.2 Instuct 1B and 3B to the model list. (#3049)
Signed-off-by: Adam Treat <[email protected]>
1 parent e736533 commit 4547283

File tree

3 files changed

+57
-24
lines changed

3 files changed

+57
-24
lines changed

‎gpt4all-chat/metadata/latestnews.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,3 +9,4 @@ GPT4All v3.4.0 was released on October 8th. Changes include:
99
* **Forgetful Model Fixes:** Issues with the "Redo last chat response" button, and with continuing chats from previous sessions, have been fixed.
1010
* **Chat Saving Improvements:** On exit, GPT4All will no longer save chats that are not new or modified. As a bonus, downgrading without losing access to all chats will be possible in the future, should the need arise.
1111
* **UI Fixes:** The model list no longer scrolls to the top when you start downloading a model.
12+
* **New Models:** LLama 3.2 Instruct 3B and 1B models now available in model list.

‎gpt4all-chat/metadata/models3.json‎

Lines changed: 55 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,38 @@
1717
},
1818
{
1919
"order": "b",
20+
"md5sum": "27b44e8ae1817525164ddf4f8dae8af4",
21+
"name": "Llama 3.2 3B Instruct",
22+
"filename": "Llama-3.2-3B-Instruct-Q4_0.gguf",
23+
"filesize": "1921909280",
24+
"requires": "3.4.0",
25+
"ramrequired": "4",
26+
"parameters": "3 billion",
27+
"quant": "q4_0",
28+
"type": "LLaMA3",
29+
"description": "<ul><li>Fast responses</li><li>Instruct model</li><li>Multilingual dialogue use</li><li>Agentic system capable</li><li>Trained by Meta</li><li>License: <a href=\"https://llama.meta.com/llama3_2/license/\">Meta Llama 3.2 Community License</a></li></ul>",
30+
"url": "https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_0.gguf",
31+
"promptTemplate": "<|start_header_id|>user<|end_header_id|>\n\n%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n%2",
32+
"systemPrompt": "<|start_header_id|>system<|end_header_id|>\nCutting Knowledge Date: December 2023\n\nYou are a helpful assistant.<|eot_id|>"
33+
},
34+
{
35+
"order": "c",
36+
"md5sum": "48ff0243978606fdba19d899b77802fc",
37+
"name": "Llama 3.2 1B Instruct",
38+
"filename": "Llama-3.2-1B-Instruct-Q4_0.gguf",
39+
"filesize": "773025920",
40+
"requires": "3.4.0",
41+
"ramrequired": "2",
42+
"parameters": "1 billion",
43+
"quant": "q4_0",
44+
"type": "LLaMA3",
45+
"description": "<ul><li>Fast responses</li><li>Instruct model</li><li>Multilingual dialogue use</li><li>Agentic system capable</li><li>Trained by Meta</li><li>License: <a href=\"https://llama.meta.com/llama3_2/license/\">Meta Llama 3.2 Community License</a></li></ul>",
46+
"url": "https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_0.gguf",
47+
"promptTemplate": "<|start_header_id|>user<|end_header_id|>\n\n%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n%2",
48+
"systemPrompt": "<|start_header_id|>system<|end_header_id|>\nCutting Knowledge Date: December 2023\n\nYou are a helpful assistant.<|eot_id|>"
49+
},
50+
{
51+
"order": "d",
2052
"md5sum": "a5f6b4eabd3992da4d7fb7f020f921eb",
2153
"name": "Nous Hermes 2 Mistral DPO",
2254
"filename": "Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf",
@@ -32,7 +64,7 @@
3264
"systemPrompt": ""
3365
},
3466
{
35-
"order": "c",
67+
"order": "e",
3668
"md5sum": "97463be739b50525df56d33b26b00852",
3769
"name": "Mistral Instruct",
3870
"filename": "mistral-7b-instruct-v0.1.Q4_0.gguf",
@@ -48,7 +80,7 @@
4880
"promptTemplate": "[INST] %1 [/INST]"
4981
},
5082
{
51-
"order": "d",
83+
"order": "f",
5284
"md5sum": "8a9c75bcd8a66b7693f158ec96924eeb",
5385
"name": "Llama 3.1 8B Instruct 128k",
5486
"filename": "Meta-Llama-3.1-8B-Instruct-128k-Q4_0.gguf",
@@ -64,7 +96,7 @@
6496
"systemPrompt": "<|start_header_id|>system<|end_header_id|>\nCutting Knowledge Date: December 2023\n\nYou are a helpful assistant.<|eot_id|>"
6597
},
6698
{
67-
"order": "e",
99+
"order": "g",
68100
"md5sum": "f692417a22405d80573ac10cb0cd6c6a",
69101
"name": "Mistral OpenOrca",
70102
"filename": "mistral-7b-openorca.gguf2.Q4_0.gguf",
@@ -80,7 +112,7 @@
80112
"systemPrompt": "<|im_start|>system\nYou are MistralOrca, a large language model trained by Alignment Lab AI.\n<|im_end|>\n"
81113
},
82114
{
83-
"order": "f",
115+
"order": "h",
84116
"md5sum": "c4c78adf744d6a20f05c8751e3961b84",
85117
"name": "GPT4All Falcon",
86118
"filename": "gpt4all-falcon-newbpe-q4_0.gguf",
@@ -96,7 +128,7 @@
96128
"promptTemplate": "### Instruction:\n%1\n\n### Response:\n"
97129
},
98130
{
99-
"order": "g",
131+
"order": "i",
100132
"md5sum": "00c8593ba57f5240f59662367b3ed4a5",
101133
"name": "Orca 2 (Medium)",
102134
"filename": "orca-2-7b.Q4_0.gguf",
@@ -111,7 +143,7 @@
111143
"url": "https://gpt4all.io/models/gguf/orca-2-7b.Q4_0.gguf"
112144
},
113145
{
114-
"order": "h",
146+
"order": "j",
115147
"md5sum": "3c0d63c4689b9af7baa82469a6f51a19",
116148
"name": "Orca 2 (Full)",
117149
"filename": "orca-2-13b.Q4_0.gguf",
@@ -126,7 +158,7 @@
126158
"url": "https://gpt4all.io/models/gguf/orca-2-13b.Q4_0.gguf"
127159
},
128160
{
129-
"order": "i",
161+
"order": "k",
130162
"md5sum": "5aff90007499bce5c64b1c0760c0b186",
131163
"name": "Wizard v1.2",
132164
"filename": "wizardlm-13b-v1.2.Q4_0.gguf",
@@ -141,7 +173,7 @@
141173
"url": "https://gpt4all.io/models/gguf/wizardlm-13b-v1.2.Q4_0.gguf"
142174
},
143175
{
144-
"order": "j",
176+
"order": "l",
145177
"md5sum": "31b47b4e8c1816b62684ac3ca373f9e1",
146178
"name": "Ghost 7B v0.9.1",
147179
"filename": "ghost-7b-v0.9.1-Q4_0.gguf",
@@ -157,7 +189,7 @@
157189
"systemPrompt": "<|system|>\nYou are Ghost created by Lam Hieu. You are a helpful and knowledgeable assistant. You like to help and always give honest information, in its original language. In communication, you are always respectful, equal and promote positive behavior.\n</s>"
158190
},
159191
{
160-
"order": "k",
192+
"order": "m",
161193
"md5sum": "3d12810391d04d1153b692626c0c6e16",
162194
"name": "Hermes",
163195
"filename": "nous-hermes-llama2-13b.Q4_0.gguf",
@@ -173,7 +205,7 @@
173205
"promptTemplate": "### Instruction:\n%1\n\n### Response:\n"
174206
},
175207
{
176-
"order": "l",
208+
"order": "n",
177209
"md5sum": "40388eb2f8d16bb5d08c96fdfaac6b2c",
178210
"name": "Snoozy",
179211
"filename": "gpt4all-13b-snoozy-q4_0.gguf",
@@ -188,7 +220,7 @@
188220
"url": "https://gpt4all.io/models/gguf/gpt4all-13b-snoozy-q4_0.gguf"
189221
},
190222
{
191-
"order": "m",
223+
"order": "o",
192224
"md5sum": "15dcb4d7ea6de322756449c11a0b7545",
193225
"name": "MPT Chat",
194226
"filename": "mpt-7b-chat-newbpe-q4_0.gguf",
@@ -205,7 +237,7 @@
205237
"systemPrompt": "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>\n"
206238
},
207239
{
208-
"order": "n",
240+
"order": "p",
209241
"md5sum": "ab5d8e8a2f79365ea803c1f1d0aa749d",
210242
"name": "MPT Chat",
211243
"filename": "mpt-7b-chat.gguf4.Q4_0.gguf",
@@ -221,7 +253,7 @@
221253
"systemPrompt": "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>\n"
222254
},
223255
{
224-
"order": "o",
256+
"order": "q",
225257
"md5sum": "f8347badde9bfc2efbe89124d78ddaf5",
226258
"name": "Phi-3 Mini Instruct",
227259
"filename": "Phi-3-mini-4k-instruct.Q4_0.gguf",
@@ -237,7 +269,7 @@
237269
"systemPrompt": ""
238270
},
239271
{
240-
"order": "p",
272+
"order": "r",
241273
"md5sum": "0e769317b90ac30d6e09486d61fefa26",
242274
"name": "Mini Orca (Small)",
243275
"filename": "orca-mini-3b-gguf2-q4_0.gguf",
@@ -253,7 +285,7 @@
253285
"systemPrompt": "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
254286
},
255287
{
256-
"order": "q",
288+
"order": "s",
257289
"md5sum": "c232f17e09bca4b7ee0b5b1f4107c01e",
258290
"disableGUI": "true",
259291
"name": "Replit",
@@ -270,7 +302,7 @@
270302
"url": "https://gpt4all.io/models/gguf/replit-code-v1_5-3b-newbpe-q4_0.gguf"
271303
},
272304
{
273-
"order": "r",
305+
"order": "t",
274306
"md5sum": "70841751ccd95526d3dcfa829e11cd4c",
275307
"disableGUI": "true",
276308
"name": "Starcoder",
@@ -287,7 +319,7 @@
287319
"url": "https://gpt4all.io/models/gguf/starcoder-newbpe-q4_0.gguf"
288320
},
289321
{
290-
"order": "s",
322+
"order": "u",
291323
"md5sum": "e973dd26f0ffa6e46783feaea8f08c83",
292324
"disableGUI": "true",
293325
"name": "Rift coder",
@@ -304,7 +336,7 @@
304336
"url": "https://gpt4all.io/models/gguf/rift-coder-v0-7b-q4_0.gguf"
305337
},
306338
{
307-
"order": "t",
339+
"order": "v",
308340
"md5sum": "e479e6f38b59afc51a470d1953a6bfc7",
309341
"disableGUI": "true",
310342
"name": "SBert",
@@ -322,7 +354,7 @@
322354
"url": "https://gpt4all.io/models/gguf/all-MiniLM-L6-v2-f16.gguf"
323355
},
324356
{
325-
"order": "u",
357+
"order": "w",
326358
"md5sum": "dd90e2cb7f8e9316ac3796cece9883b5",
327359
"name": "SBert",
328360
"filename": "all-MiniLM-L6-v2.gguf2.f16.gguf",
@@ -338,7 +370,7 @@
338370
"url": "https://gpt4all.io/models/gguf/all-MiniLM-L6-v2.gguf2.f16.gguf"
339371
},
340372
{
341-
"order": "v",
373+
"order": "x",
342374
"md5sum": "919de4dd6f25351bcb0223790db1932d",
343375
"name": "EM German Mistral",
344376
"filename": "em_german_mistral_v01.Q4_0.gguf",
@@ -354,7 +386,7 @@
354386
"systemPrompt": "Du bist ein hilfreicher Assistent. "
355387
},
356388
{
357-
"order": "w",
389+
"order": "y",
358390
"md5sum": "60ea031126f82db8ddbbfecc668315d2",
359391
"disableGUI": "true",
360392
"name": "Nomic Embed Text v1",
@@ -371,7 +403,7 @@
371403
"url": "https://gpt4all.io/models/gguf/nomic-embed-text-v1.f16.gguf"
372404
},
373405
{
374-
"order": "x",
406+
"order": "z",
375407
"md5sum": "a5401e7f7e46ed9fcaed5b60a281d547",
376408
"disableGUI": "true",
377409
"name": "Nomic Embed Text v1.5",
@@ -388,7 +420,7 @@
388420
"url": "https://gpt4all.io/models/gguf/nomic-embed-text-v1.5.f16.gguf"
389421
},
390422
{
391-
"order": "z",
423+
"order": "zzz",
392424
"md5sum": "a8c5a783105f87a481543d4ed7d7586d",
393425
"name": "Qwen2-1.5B-Instruct",
394426
"filename": "qwen2-1_5b-instruct-q4_0.gguf",

‎gpt4all-chat/metadata/release.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -216,7 +216,7 @@
216216
},
217217
{
218218
"version": "3.4.0",
219-
"notes": "* **Attached Files:** You can now attach a small Microsoft Excel spreadsheet (.xlsx) to a chat message and ask the model about it.\n* **LocalDocs Accuracy:** The LocalDocs algorithm has been enhanced to find more accurate references for some queries.\n* **Word Document Support:** LocalDocs now supports Microsoft Word (.docx) documents natively.\n * **IMPORTANT NOTE:** If .docx files are not found, make sure Settings > LocalDocs > Allowed File Extensions includes \"docx\".\n* **Forgetful Model Fixes:** Issues with the \"Redo last chat response\" button, and with continuing chats from previous sessions, have been fixed.\n* **Chat Saving Improvements:** On exit, GPT4All will no longer save chats that are not new or modified. As a bonus, downgrading without losing access to all chats will be possible in the future, should the need arise.\n* **UI Fixes:** The model list no longer scrolls to the top when you start downloading a model.\n",
219+
"notes": "* **Attached Files:** You can now attach a small Microsoft Excel spreadsheet (.xlsx) to a chat message and ask the model about it.\n* **LocalDocs Accuracy:** The LocalDocs algorithm has been enhanced to find more accurate references for some queries.\n* **Word Document Support:** LocalDocs now supports Microsoft Word (.docx) documents natively.\n * **IMPORTANT NOTE:** If .docx files are not found, make sure Settings > LocalDocs > Allowed File Extensions includes \"docx\".\n* **Forgetful Model Fixes:** Issues with the \"Redo last chat response\" button, and with continuing chats from previous sessions, have been fixed.\n* **Chat Saving Improvements:** On exit, GPT4All will no longer save chats that are not new or modified. As a bonus, downgrading without losing access to all chats will be possible in the future, should the need arise.\n* **UI Fixes:** The model list no longer scrolls to the top when you start downloading a model.\n* **New Models:** LLama 3.2 Instruct 3B and 1B models now available in model list.",
220220
"contributors": "* Jared Van Bortel (Nomic AI)\n* Adam Treat (Nomic AI)\n* Andriy Mulyar (Nomic AI)\n* Ikko Eltociear Ashimine (`@eltociear`)\n* Victor Emanuel (`@SINAPSA-IC`)\n* Shiranui (`@supersonictw`)"
221221
}
222222
]

0 commit comments

Comments
 (0)