Track .safetensors files with LFS
Browse files- config.json +43 -0
- generation_config.json +7 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- trainer_state.json +0 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CohereForAI/aya-23-8B",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaCohereForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 5,
|
9 |
+
"eos_token_id": 255001,
|
10 |
+
"freeze_mm_mlp_adapter": false,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"image_aspect_ratio": "pad",
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 14336,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"logit_scale": 0.0625,
|
18 |
+
"max_position_embeddings": 8192,
|
19 |
+
"mm_hidden_size": 768,
|
20 |
+
"mm_patch_merge_type": "flat",
|
21 |
+
"mm_projector_lr": null,
|
22 |
+
"mm_projector_type": "mlp2x_gelu",
|
23 |
+
"mm_use_im_patch_token": false,
|
24 |
+
"mm_use_im_start_end": false,
|
25 |
+
"mm_vision_select_feature": "patch",
|
26 |
+
"mm_vision_select_layer": -2,
|
27 |
+
"mm_vision_tower": "google/siglip-base-patch16-256-multilingual",
|
28 |
+
"model_type": "llava_cohere",
|
29 |
+
"num_attention_heads": 32,
|
30 |
+
"num_hidden_layers": 32,
|
31 |
+
"num_key_value_heads": 8,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"rope_theta": 10000,
|
34 |
+
"tokenizer_model_max_length": 2048,
|
35 |
+
"tokenizer_padding_side": "right",
|
36 |
+
"torch_dtype": "bfloat16",
|
37 |
+
"transformers_version": "4.42.3",
|
38 |
+
"tune_mm_mlp_adapter": false,
|
39 |
+
"use_cache": true,
|
40 |
+
"use_mm_proj": true,
|
41 |
+
"use_qk_norm": false,
|
42 |
+
"vocab_size": 256000
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 5,
|
4 |
+
"eos_token_id": 255001,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba08f8143bd9ac58b44074d83e4e3a49119b511bc33b1a3f1b04196f4b837d3
|
3 |
+
size 4915779696
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48a80f2976b5d84ff04398079ded72d845e601adec009f7d85d6df44d4ab97af
|
3 |
+
size 4915824704
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f34980515b521a65804dd88871ad87dec30462db6770ab51574054923e0038cb
|
3 |
+
size 4999719592
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:840ed6041cb035306a234d7085cf748490439fe6a6c7887038d6fcb06c21b87f
|
3 |
+
size 1413046272
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|