Spaces:
Running
Running
Upload 4 files
Browse files
.gitattributes
CHANGED
@@ -40,3 +40,4 @@ models/GLM-4-0414/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
40 |
models/Mistral-Small-3.1-2503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
41 |
models/Command-A-03-2025/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
42 |
models/Aya-expanse/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
40 |
models/Mistral-Small-3.1-2503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
41 |
models/Command-A-03-2025/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
42 |
models/Aya-expanse/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
43 |
+
models/Mistral-Small-3.1-2503/tekken.json filter=lfs diff=lfs merge=lfs -text
|
models/Mistral-Small-3.1-2503/config.json
CHANGED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Mistral3ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"image_token_index": 10,
|
6 |
+
"model_type": "mistral3",
|
7 |
+
"multimodal_projector_bias": false,
|
8 |
+
"projector_hidden_act": "gelu",
|
9 |
+
"spatial_merge_size": 2,
|
10 |
+
"text_config": {
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"head_dim": 128,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 5120,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 32768,
|
17 |
+
"max_position_embeddings": 131072,
|
18 |
+
"model_type": "mistral",
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_hidden_layers": 40,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_theta": 1000000000.0,
|
24 |
+
"sliding_window": null,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 131072
|
27 |
+
},
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.50.0.dev0",
|
30 |
+
"vision_config": {
|
31 |
+
"attention_dropout": 0.0,
|
32 |
+
"head_dim": 64,
|
33 |
+
"hidden_act": "gelu",
|
34 |
+
"hidden_size": 1024,
|
35 |
+
"image_size": 1540,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 4096,
|
38 |
+
"model_type": "pixtral",
|
39 |
+
"num_attention_heads": 16,
|
40 |
+
"num_channels": 3,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"patch_size": 14,
|
43 |
+
"rope_theta": 10000.0
|
44 |
+
},
|
45 |
+
"vision_feature_layer": -1
|
46 |
+
}
|
models/Mistral-Small-3.1-2503/tekken.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c604f35d1035f534519622c0ec83fed6184978d4fdee92a5bd2a50bc05438094
|
3 |
+
size 14801330
|
models/Mistral-Small-3.1-2503/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
3 |
+
size 17078037
|
models/Mistral-Small-3.1-2503/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|