Upload folder using huggingface_hub
Browse files- checkpoints/checkpoint-34495/config.json +42 -0
- checkpoints/checkpoint-34495/generation_config.json +6 -0
- checkpoints/checkpoint-34495/model.safetensors +3 -0
- checkpoints/checkpoint-34495/optimizer.pt +3 -0
- checkpoints/checkpoint-34495/rng_state.pth +3 -0
- checkpoints/checkpoint-34495/scheduler.pt +3 -0
- checkpoints/checkpoint-34495/trainer_state.json +0 -0
- checkpoints/checkpoint-34495/training_args.bin +3 -0
checkpoints/checkpoint-34495/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/codegen-350M-mono",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"CodeGenForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "codegen",
|
| 15 |
+
"n_ctx": 2048,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 20,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"resid_pdrop": 0.0,
|
| 22 |
+
"rotary_dim": 32,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50,
|
| 33 |
+
"temperature": 1.0
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.43.4",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 51200
|
| 42 |
+
}
|
checkpoints/checkpoint-34495/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.43.4"
|
| 6 |
+
}
|
checkpoints/checkpoint-34495/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2a7bbb913d5559a43817b09bc973ed7106cde772edf4c00006a6016ab25eefc
|
| 3 |
+
size 1426867192
|
checkpoints/checkpoint-34495/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf92d9b7537d069019c1ca7a9f4401bf4f79901ec899fc6d220137f74a035982
|
| 3 |
+
size 2853838475
|
checkpoints/checkpoint-34495/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66ae1491e22b10369b6fc0e39d09516e8984158ba68756afff1e9702e927d375
|
| 3 |
+
size 14645
|
checkpoints/checkpoint-34495/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f74b8450b3850d75bdaac2c58de7033055fe04f3cec80ba5c34b2faaa514884a
|
| 3 |
+
size 1465
|
checkpoints/checkpoint-34495/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/checkpoint-34495/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1c3babd7ab0462b4f531c01977c5564178ecf4790c6e45deb4ccef51fd55316
|
| 3 |
+
size 5585
|