simonykq commited on
Commit
962ade5
·
verified ·
1 Parent(s): 773534f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - financial
6
+ - transactions
7
+ - llama
8
+ - foundation-model
9
+ - embeddings
10
+ pipeline_tag: feature-extraction
11
+ ---
12
+
13
+ # NVIDIA Transaction Decoder Foundation Model (~29M)
14
+
15
+ Pretrained checkpoint from the [NVIDIA Build Your Own Transaction Foundation Model](https://github.com/NVIDIA-AI-Blueprints/transaction-foundation-model) developer example, as described in the [NVIDIA Technical Blog](https://developer.nvidia.com/blog/build-your-own-transaction-foundation-model-for-financial-intelligence/).
16
+
17
+ - Architecture: Llama decoder-only (~29M params, hidden 512, 8 layers, GQA)
18
+ - Vocabulary: ~6,251 domain-specific financial transaction tokens
19
+ - Trained ~3,000 steps on IBM TabFormer with NeMo AutoModel
20
+ - Load with `AutoModelForCausalLM.from_pretrained(...)` and extract last-token embeddings
21
+
22
+ This Hub mirror exists so Spaces / Transformers can load the Git LFS checkpoint published under `models/decoder-foundation-model/` in the upstream GitHub repo.
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 512,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 1408,
11
+ "max_position_embeddings": 8192,
12
+ "mlp_bias": false,
13
+ "model_type": "llama",
14
+ "nemo_version": "0.1.1",
15
+ "num_attention_heads": 8,
16
+ "num_hidden_layers": 8,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.53.3",
25
+ "use_cache": true,
26
+ "vocab_size": 6251
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.53.3"
7
+ }
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c5899c2ab0146c209207d67efc65dda882f4966ae09877b2580c14bcb62cbe
3
+ size 57917064
model.safetensors.index.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 57908224
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
7
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
8
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
9
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
10
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
14
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
16
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
17
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
18
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
19
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
23
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
25
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
26
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
27
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
28
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
29
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
30
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
31
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
32
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
33
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
34
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
35
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
36
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
37
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
38
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
39
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
40
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
41
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
42
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
43
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
44
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
45
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
46
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
47
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
48
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
49
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
50
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
51
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
52
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
53
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
54
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
55
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
56
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
57
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
58
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
59
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
60
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
61
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
62
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
63
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
64
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
65
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
66
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
67
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
68
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
69
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
70
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
71
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
72
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
73
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
74
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
75
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
76
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
77
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
78
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
79
+ "model.norm.weight": "model-00001-of-00001.safetensors",
80
+ "lm_head.weight": "model-00001-of-00001.safetensors"
81
+ }
82
+ }