Add weights
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +6 -0
- config.json +5 -0
- mlc-chat-config.json +84 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_100.bin +3 -0
- params_shard_101.bin +3 -0
- params_shard_102.bin +3 -0
- params_shard_103.bin +3 -0
- params_shard_104.bin +3 -0
- params_shard_105.bin +3 -0
- params_shard_106.bin +3 -0
- params_shard_107.bin +3 -0
- params_shard_108.bin +3 -0
- params_shard_109.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_110.bin +3 -0
- params_shard_111.bin +3 -0
- params_shard_112.bin +3 -0
- params_shard_113.bin +3 -0
- params_shard_114.bin +3 -0
- params_shard_115.bin +3 -0
- params_shard_116.bin +3 -0
- params_shard_117.bin +3 -0
- params_shard_118.bin +3 -0
- params_shard_119.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_120.bin +3 -0
- params_shard_121.bin +3 -0
- params_shard_122.bin +3 -0
- params_shard_123.bin +3 -0
- params_shard_124.bin +3 -0
- params_shard_125.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,9 @@
|
|
1 |
---
|
2 |
license: gemma
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
1 |
---
|
2 |
license: gemma
|
3 |
+
base_model: google/gemma-2-9b-it
|
4 |
+
base_model_relation: quantized
|
5 |
+
library_name: mlc-llm
|
6 |
+
pipeline_tag: text-generation
|
7 |
---
|
8 |
+
|
9 |
+
4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it).
|
config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"quantization_config": {
|
3 |
+
"bits": 4
|
4 |
+
}
|
5 |
+
}
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "gemma2",
|
4 |
+
"quantization": "w4a16g128",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 3584,
|
7 |
+
"intermediate_size": 14336,
|
8 |
+
"attention_bias": false,
|
9 |
+
"num_attention_heads": 16,
|
10 |
+
"num_key_value_heads": 8,
|
11 |
+
"head_dim": 256,
|
12 |
+
"num_hidden_layers": 42,
|
13 |
+
"rms_norm_eps": 1e-06,
|
14 |
+
"vocab_size": 256000,
|
15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
16 |
+
"position_embedding_base": 10000.0,
|
17 |
+
"context_window_size": 4096,
|
18 |
+
"prefill_chunk_size": 128,
|
19 |
+
"tensor_parallel_shards": 1,
|
20 |
+
"max_batch_size": 128,
|
21 |
+
"attn_logit_softcapping": 50.0,
|
22 |
+
"final_logit_softcapping": 30.0,
|
23 |
+
"query_pre_attn_scalar": 256,
|
24 |
+
"sliding_window": 4096
|
25 |
+
},
|
26 |
+
"vocab_size": 256000,
|
27 |
+
"context_window_size": 4096,
|
28 |
+
"sliding_window_size": -1,
|
29 |
+
"prefill_chunk_size": 128,
|
30 |
+
"attention_sink_size": -1,
|
31 |
+
"tensor_parallel_shards": 1,
|
32 |
+
"pipeline_parallel_stages": 1,
|
33 |
+
"temperature": 1.0,
|
34 |
+
"presence_penalty": 0.0,
|
35 |
+
"frequency_penalty": 0.0,
|
36 |
+
"repetition_penalty": 1.0,
|
37 |
+
"top_p": 1.0,
|
38 |
+
"tokenizer_files": [
|
39 |
+
"tokenizer.model",
|
40 |
+
"tokenizer.json",
|
41 |
+
"tokenizer_config.json"
|
42 |
+
],
|
43 |
+
"tokenizer_info": {
|
44 |
+
"token_postproc_method": "byte_fallback",
|
45 |
+
"prepend_space_in_encode": false,
|
46 |
+
"strip_space_in_decode": false
|
47 |
+
},
|
48 |
+
"conv_template": {
|
49 |
+
"name": "gemma_instruction",
|
50 |
+
"system_template": "{system_message}",
|
51 |
+
"system_message": "",
|
52 |
+
"system_prefix_token_ids": [
|
53 |
+
2
|
54 |
+
],
|
55 |
+
"add_role_after_system_message": true,
|
56 |
+
"roles": {
|
57 |
+
"user": "<start_of_turn>user",
|
58 |
+
"assistant": "<start_of_turn>model"
|
59 |
+
},
|
60 |
+
"role_templates": {
|
61 |
+
"user": "{user_message}",
|
62 |
+
"assistant": "{assistant_message}",
|
63 |
+
"tool": "{tool_message}"
|
64 |
+
},
|
65 |
+
"messages": [],
|
66 |
+
"seps": [
|
67 |
+
"<end_of_turn>\n"
|
68 |
+
],
|
69 |
+
"role_content_sep": "\n",
|
70 |
+
"role_empty_sep": "\n",
|
71 |
+
"stop_str": [
|
72 |
+
"<end_of_turn>"
|
73 |
+
],
|
74 |
+
"stop_token_ids": [
|
75 |
+
1,
|
76 |
+
107
|
77 |
+
],
|
78 |
+
"function_string": "",
|
79 |
+
"use_function_calling": false
|
80 |
+
},
|
81 |
+
"pad_token_id": 0,
|
82 |
+
"bos_token_id": 2,
|
83 |
+
"eos_token_id": 1
|
84 |
+
}
|
ndarray-cache.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f7f2db24c4f29a7cd63f3ca1ce933f6836f746795ca8b174037b70410b4c927
|
3 |
+
size 458752000
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b299b226a2dab9e6b8bced2d82ff1822617a08fe3cda399dd3f306acb5e5864c
|
3 |
+
size 25690112
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c97a4eea5493443135fb243c1fe7ae0bcfd663209b0207a0b85901cba654ea7d
|
3 |
+
size 51380224
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e80aa15cc4bd4e96e844f0490eae7c69c5244b3836b08a4b5f26e5c6d9434100
|
3 |
+
size 25976832
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:828b910b86d99de04273eaca8f0febb0e4b05c7afef665be3ae5a5a95dd316fe
|
3 |
+
size 25690112
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e0d35133aaa438ae704dd20bdf4ebc4a62921cbd912585b404cfa75a2ec4b2a
|
3 |
+
size 51380224
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f896eabdb3290a7c6a3e05788dea9b49e63063a84751d8245605370af5825103
|
3 |
+
size 25145344
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b20454daf1d5895019afc6fac56f3a65e3cfc8b27331b481e10926204c180d3
|
3 |
+
size 25690112
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f1da35ee268cc58474019f7c828eaef61e91a1e8f3852ed0f127c43b0d7017e
|
3 |
+
size 51380224
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f94163933098d93dbc130ab77a6610ed9cc0c19d828a34502c7a977d4fd5b67e
|
3 |
+
size 25145344
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21c1f24792e8214d0bb4d4a1830b293661a59afad1d21dc58eac7b99d303e20
|
3 |
+
size 25690112
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fb0ac32bf65ba957d529812bcf3095482601ab41c471ab44c43e642edebe04b
|
3 |
+
size 51380224
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1856b2c79f3ca987c8481992853ce0b8b9a184ea8eb25a80fe37823a9b6119ff
|
3 |
+
size 25145344
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:117bbafc952d0ff02c85655ca421dabebfd386490dfba5e32532d167216473e7
|
3 |
+
size 25145344
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b7ec1d0c2f397c3b3fc6426975fd8c6104515f18c716155ea2f54733a5f6b08
|
3 |
+
size 25690112
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8ae8abe8f88d14bb3dc9d8d82ab5a9c95efc751a876bda1bc26a8359c07948
|
3 |
+
size 51380224
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:636642ceb866a19bc97196e0dcfba9f0c4475107ac727d0cf9f27e29ecf65a7b
|
3 |
+
size 25145344
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c873209052d13776c340464802bc3b18d14ae44ff0be7f43164b5ac13430babe
|
3 |
+
size 25690112
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f611b9227c72b0b2e65264889490886614e806e906d65cc15b8210aa5c91b6be
|
3 |
+
size 51380224
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cba2a9842712c53fd5e95591545d8ba4bd41a634f520d61d2d74ef8adccb004
|
3 |
+
size 25145344
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081d552340ea534950ed392b29d0ee887afca142a41a5062416cca346ece84fb
|
3 |
+
size 25690112
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3073e32e3e1782b21e753abe75ed2d52785df33bff19d736b9db1debb70252cd
|
3 |
+
size 51380224
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4435aaf4b535a732da15562fdead7f15bfc2f2552572ebef9aa27ac72139bf6c
|
3 |
+
size 25145344
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1e245ef7e88171bfc377811a8d086a49500971ad9ef0d71970d30ca768e94e
|
3 |
+
size 25690112
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04524f9903f7b23f39e14066377fe59071bcfa5ab6573ac854152b135d06bb33
|
3 |
+
size 25690112
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfa6f1794a5dc18a0dca1e852bcd7755816690fe34040c3d6eeede00e4dd220c
|
3 |
+
size 51380224
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb322be314a60dbead05f313a4bb61b3ad02a939b41e1d7f302320bb1db658e2
|
3 |
+
size 25145344
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21d0ebb474eccaa7bed34d70ee8be149cc486dd2aa89902d8bae525864d38d1e
|
3 |
+
size 25690112
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:500e9cc2170acf419797427c18fa2f2d94e2b16c13e8a81db9f3031267ecfafc
|
3 |
+
size 51380224
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd930914a06650d248f9f81542bdc348e1ec8a93289faff87c44c18086d5592d
|
3 |
+
size 25145344
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2f4b46d28fbdaf8a17264ef1054e02ebc85ad265f834baa0f686c36d626418c
|
3 |
+
size 22715392
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de97eaecc00ba0671df350abb1eee16ad3952c1f33931d171479b15bcc5b873
|
3 |
+
size 51380224
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08d0d1ab243a733a055e5c4388358b9aa3c89afb4197fbb103cdd5353a54b803
|
3 |
+
size 25145344
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe0e4f6f8698f52aee1e973ce1d4805001feeeb270a96872b0968c796269b21
|
3 |
+
size 25690112
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43e4b5a2880527a557c61e5ec8d7675c167e42e637d08f3c9aa20536733ee691
|
3 |
+
size 51380224
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd3bc4a05e7a6472885448d463a9dfc52d0bafad13584582ff6f756526af5652
|
3 |
+
size 25145344
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2fbf7b24059c1ca81d6b672f3e1c903b9147e8379042518053f7a8872b551b7
|
3 |
+
size 25690112
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dad5b8a9f17ef32bc45753d980514dba3316bbec2c4f38d8eff6decee84e96f
|
3 |
+
size 51380224
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aefce0d8c44996cc538fd6a67f61ac197b26fa2ec41d0ba366db28adfbc3d47
|
3 |
+
size 51380224
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe79d02cc6a27929cd45c974e8fdcee28ae5ce53c6a641428395133d178a2423
|
3 |
+
size 25145344
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0f83f2ca6d65f6fefa617b4f43b91dd3aefe9a5f7351a7cced59e65d88e1a02
|
3 |
+
size 51380224
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cf2ea5830ebc3c4b609d1030713eaceb2d7c39f96d2f048ef24bfd533b4db6a
|
3 |
+
size 24313856
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c38be80ab0b55e7f5111e10ae67fec4de07bb73192718073582f418a932806d
|
3 |
+
size 25690112
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2101db93c8b842aa3bd963da327c810536666a1feb97398d69c52eb9c2e78a59
|
3 |
+
size 51380224
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d7e0609a9e632b8883ba0841d6fd6dcd431e9c3d293221eebfdbd1c3aa3b6f8
|
3 |
+
size 25145344
|