Hugging Face's logo

nvidia
/
audio-flamingo-3-hf

Audio-Text-to-Text
Transformers
Safetensors
English
audioflamingo3
text2text-generation
audio
reasoning
audio understanding
ASR
Model card Files
xet
Community
2
SreyanG-NVIDIA commited on
Commit
1b7715c
·
verified ·
1 Parent(s): 473eee7

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. think/adapter_config.json +74 -74
  2. think/adapter_model.safetensors +1 -1
  3. think/non_lora_trainables.bin +1 -1
think/adapter_config.json CHANGED
@@ -24,94 +24,94 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "model.layers.1.self_attn.q_proj",
28
- "model.layers.24.self_attn.v_proj",
29
- "model.layers.18.self_attn.q_proj",
30
- "model.layers.23.self_attn.q_proj",
31
- "model.layers.25.self_attn.q_proj",
32
- "model.layers.11.self_attn.v_proj",
33
- "model.layers.19.self_attn.v_proj",
34
- "model.layers.13.self_attn.q_proj",
35
- "model.layers.5.self_attn.q_proj",
36
- "model.layers.2.self_attn.q_proj",
37
- "model.layers.18.self_attn.v_proj",
38
- "model.layers.4.self_attn.v_proj",
39
- "model.layers.9.self_attn.k_proj",
40
- "model.layers.15.self_attn.k_proj",
41
- "model.layers.20.self_attn.k_proj",
42
- "model.layers.23.self_attn.k_proj",
43
  "model.layers.3.self_attn.v_proj",
44
- "model.layers.11.self_attn.k_proj",
45
- "model.layers.16.self_attn.q_proj",
46
- "model.layers.10.self_attn.k_proj",
47
- "model.layers.1.self_attn.v_proj",
48
  "model.layers.17.self_attn.v_proj",
49
- "model.layers.4.self_attn.k_proj",
50
- "model.layers.18.self_attn.k_proj",
51
- "model.layers.8.self_attn.v_proj",
52
- "o_proj",
53
- "model.layers.0.self_attn.k_proj",
54
- "model.layers.3.self_attn.k_proj",
55
- "model.layers.22.self_attn.q_proj",
56
- "model.layers.13.self_attn.v_proj",
57
- "model.layers.1.self_attn.k_proj",
58
- "model.layers.27.self_attn.v_proj",
59
- "model.layers.14.self_attn.v_proj",
60
- "model.layers.19.self_attn.k_proj",
61
  "model.layers.14.self_attn.k_proj",
62
- "down_proj",
 
 
 
 
 
 
 
63
  "model.layers.7.self_attn.q_proj",
64
- "model.layers.3.self_attn.q_proj",
 
 
 
 
 
 
 
65
  "model.layers.2.self_attn.k_proj",
 
 
 
 
 
 
 
66
  "model.layers.25.self_attn.v_proj",
67
- "model.layers.2.self_attn.v_proj",
68
  "model.layers.26.self_attn.k_proj",
69
- "model.layers.10.self_attn.v_proj",
70
- "model.layers.24.self_attn.k_proj",
71
- "model.layers.24.self_attn.q_proj",
72
- "model.layers.4.self_attn.q_proj",
73
  "model.layers.25.self_attn.k_proj",
74
- "model.layers.6.self_attn.k_proj",
75
- "model.layers.7.self_attn.v_proj",
76
- "model.layers.27.self_attn.k_proj",
77
- "model.layers.19.self_attn.q_proj",
78
- "gate_proj",
79
- "model.layers.5.self_attn.v_proj",
80
- "model.layers.23.self_attn.v_proj",
81
- "up_proj",
82
- "model.layers.10.self_attn.q_proj",
83
- "model.layers.14.self_attn.q_proj",
84
- "model.layers.26.self_attn.q_proj",
85
- "model.layers.11.self_attn.q_proj",
86
  "model.layers.15.self_attn.q_proj",
87
- "model.layers.6.self_attn.q_proj",
88
- "model.layers.17.self_attn.k_proj",
89
- "model.layers.17.self_attn.q_proj",
90
- "model.layers.21.self_attn.k_proj",
 
 
91
  "model.layers.12.self_attn.v_proj",
 
 
 
92
  "model.layers.13.self_attn.k_proj",
93
- "model.layers.12.self_attn.q_proj",
94
- "model.layers.22.self_attn.k_proj",
95
- "model.layers.8.self_attn.q_proj",
96
- "model.layers.20.self_attn.q_proj",
97
- "model.layers.16.self_attn.k_proj",
98
- "model.layers.5.self_attn.k_proj",
 
 
99
  "model.layers.15.self_attn.v_proj",
100
- "model.layers.9.self_attn.v_proj",
101
- "model.layers.20.self_attn.v_proj",
102
- "model.layers.6.self_attn.v_proj",
103
- "model.layers.0.self_attn.v_proj",
104
- "model.layers.22.self_attn.v_proj",
105
- "model.layers.9.self_attn.q_proj",
106
- "model.layers.8.self_attn.k_proj",
107
  "model.layers.26.self_attn.v_proj",
108
- "model.layers.7.self_attn.k_proj",
109
- "model.layers.16.self_attn.v_proj",
110
- "model.layers.21.self_attn.v_proj",
111
- "model.layers.12.self_attn.k_proj",
112
  "model.layers.21.self_attn.q_proj",
113
- "model.layers.27.self_attn.q_proj",
114
- "model.layers.0.self_attn.q_proj"
 
 
 
 
 
 
 
 
 
 
 
 
115
  ],
116
  "task_type": "CAUSAL_LM",
117
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "model.layers.5.self_attn.v_proj",
28
+ "model.layers.24.self_attn.k_proj",
29
+ "model.layers.6.self_attn.k_proj",
30
+ "model.layers.11.self_attn.q_proj",
31
+ "model.layers.1.self_attn.k_proj",
 
 
 
 
 
 
 
 
 
 
 
32
  "model.layers.3.self_attn.v_proj",
33
+ "model.layers.21.self_attn.k_proj",
34
+ "model.layers.9.self_attn.k_proj",
35
+ "model.layers.4.self_attn.v_proj",
36
+ "model.layers.22.self_attn.k_proj",
37
  "model.layers.17.self_attn.v_proj",
 
 
 
 
 
 
 
 
 
 
 
 
38
  "model.layers.14.self_attn.k_proj",
39
+ "model.layers.12.self_attn.q_proj",
40
+ "model.layers.4.self_attn.q_proj",
41
+ "model.layers.19.self_attn.v_proj",
42
+ "model.layers.9.self_attn.q_proj",
43
+ "model.layers.27.self_attn.q_proj",
44
+ "model.layers.0.self_attn.k_proj",
45
+ "model.layers.9.self_attn.v_proj",
46
+ "model.layers.23.self_attn.k_proj",
47
  "model.layers.7.self_attn.q_proj",
48
+ "model.layers.19.self_attn.q_proj",
49
+ "model.layers.14.self_attn.q_proj",
50
+ "model.layers.15.self_attn.k_proj",
51
+ "model.layers.8.self_attn.k_proj",
52
+ "gate_proj",
53
+ "model.layers.6.self_attn.v_proj",
54
+ "model.layers.5.self_attn.q_proj",
55
+ "model.layers.0.self_attn.v_proj",
56
  "model.layers.2.self_attn.k_proj",
57
+ "model.layers.0.self_attn.q_proj",
58
+ "model.layers.10.self_attn.k_proj",
59
+ "model.layers.1.self_attn.v_proj",
60
+ "model.layers.5.self_attn.k_proj",
61
+ "model.layers.7.self_attn.k_proj",
62
+ "model.layers.22.self_attn.v_proj",
63
+ "model.layers.18.self_attn.v_proj",
64
  "model.layers.25.self_attn.v_proj",
65
+ "model.layers.1.self_attn.q_proj",
66
  "model.layers.26.self_attn.k_proj",
67
+ "model.layers.8.self_attn.q_proj",
 
 
 
68
  "model.layers.25.self_attn.k_proj",
 
 
 
 
 
 
 
 
 
 
 
 
69
  "model.layers.15.self_attn.q_proj",
70
+ "model.layers.13.self_attn.v_proj",
71
+ "up_proj",
72
+ "model.layers.24.self_attn.v_proj",
73
+ "model.layers.16.self_attn.v_proj",
74
+ "model.layers.16.self_attn.k_proj",
75
+ "model.layers.2.self_attn.v_proj",
76
  "model.layers.12.self_attn.v_proj",
77
+ "model.layers.17.self_attn.q_proj",
78
+ "model.layers.12.self_attn.k_proj",
79
+ "model.layers.18.self_attn.k_proj",
80
  "model.layers.13.self_attn.k_proj",
81
+ "model.layers.6.self_attn.q_proj",
82
+ "model.layers.18.self_attn.q_proj",
83
+ "model.layers.4.self_attn.k_proj",
84
+ "model.layers.27.self_attn.v_proj",
85
+ "model.layers.26.self_attn.q_proj",
86
+ "model.layers.11.self_attn.v_proj",
87
+ "model.layers.27.self_attn.k_proj",
88
+ "model.layers.7.self_attn.v_proj",
89
  "model.layers.15.self_attn.v_proj",
90
+ "model.layers.16.self_attn.q_proj",
91
+ "model.layers.2.self_attn.q_proj",
92
+ "o_proj",
93
+ "model.layers.22.self_attn.q_proj",
94
+ "model.layers.8.self_attn.v_proj",
 
 
95
  "model.layers.26.self_attn.v_proj",
96
+ "model.layers.3.self_attn.q_proj",
97
+ "model.layers.23.self_attn.v_proj",
98
+ "model.layers.17.self_attn.k_proj",
99
+ "model.layers.24.self_attn.q_proj",
100
  "model.layers.21.self_attn.q_proj",
101
+ "model.layers.10.self_attn.v_proj",
102
+ "model.layers.19.self_attn.k_proj",
103
+ "model.layers.14.self_attn.v_proj",
104
+ "model.layers.21.self_attn.v_proj",
105
+ "model.layers.10.self_attn.q_proj",
106
+ "model.layers.11.self_attn.k_proj",
107
+ "model.layers.23.self_attn.q_proj",
108
+ "model.layers.13.self_attn.q_proj",
109
+ "model.layers.25.self_attn.q_proj",
110
+ "model.layers.20.self_attn.q_proj",
111
+ "model.layers.20.self_attn.v_proj",
112
+ "model.layers.20.self_attn.k_proj",
113
+ "down_proj",
114
+ "model.layers.3.self_attn.k_proj"
115
  ],
116
  "task_type": "CAUSAL_LM",
117
  "trainable_token_indices": null,
think/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e4763857f6ce90fead427f2a72793cf81823a8aed2c6661ea60dfc7b021a908
3
  size 323020408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d680dd51b647dad0dd0c1b48399274b4936f5a926f0010fd702b1e00a959fff4
3
  size 323020408
think/non_lora_trainables.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4fa84b56cb4aca2c3bf635c056d7d23d3e4e11a1edd654aeb7d326e8cd34da8
3
  size 1087186621
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e858f7cc439285d42948737e413fceac35fd0eea0a050195337bc8593c0b2736
3
  size 1087186621