Upload CodeGenForCausalLM
Browse files- config.json +35 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +57 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "trl-internal-testing/tiny-random-CodeGenForCausalLM",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"CodeGenForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"attn_pdrop": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.0,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.0,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 37,
|
16 |
+
"is_decoder": true,
|
17 |
+
"layer_norm_epsilon": 1e-05,
|
18 |
+
"model_type": "codegen",
|
19 |
+
"n_ctx": 2048,
|
20 |
+
"n_embd": 32,
|
21 |
+
"n_head": 4,
|
22 |
+
"n_inner": null,
|
23 |
+
"n_layer": 5,
|
24 |
+
"n_positions": 512,
|
25 |
+
"pad_token_id": 1023,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rotary_dim": 4,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.25.1",
|
32 |
+
"type_vocab_size": 16,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 1024
|
35 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09a335e8d4b8565cf4606398c7ff1b8d312bf81dc46bd5bbfaa81aae1f3d0646
|
3 |
+
size 762697
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d7b323f5901af24c1f2e6554e457c450d6924873bf4c699f87471a4101107da
|
3 |
+
size 945397
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:656bc6a505163a36daa40712de12b2cb093278388d31e1ec85f4a2795c1f47e6
|
3 |
+
size 136379
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 1827456
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.bias": "pytorch_model-00003-of-00003.bin",
|
7 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
8 |
+
"transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"transformer.h.2.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
|
27 |
+
"transformer.h.2.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
28 |
+
"transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
|
29 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"transformer.h.2.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
32 |
+
"transformer.h.2.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
33 |
+
"transformer.h.2.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
34 |
+
"transformer.h.2.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
35 |
+
"transformer.h.3.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
|
36 |
+
"transformer.h.3.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
37 |
+
"transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
|
38 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
39 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
40 |
+
"transformer.h.3.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
41 |
+
"transformer.h.3.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
42 |
+
"transformer.h.3.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
43 |
+
"transformer.h.3.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
44 |
+
"transformer.h.4.attn.causal_mask": "pytorch_model-00002-of-00003.bin",
|
45 |
+
"transformer.h.4.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
46 |
+
"transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00002-of-00003.bin",
|
47 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
48 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"transformer.h.4.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"transformer.h.4.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"transformer.h.4.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"transformer.h.4.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"transformer.ln_f.bias": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"transformer.ln_f.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
56 |
+
}
|
57 |
+
}
|