Upload folder using huggingface_hub
Browse files- config.json +21 -38
- generation_config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,46 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "TinyPixel/
|
| 3 |
-
"_num_labels": 1,
|
| 4 |
-
"activation_function": "gelu_new",
|
| 5 |
"architectures": [
|
| 6 |
-
"
|
| 7 |
],
|
| 8 |
-
"
|
| 9 |
-
"bos_token_id":
|
| 10 |
-
"
|
| 11 |
-
"eos_token_id":
|
| 12 |
-
"
|
| 13 |
-
|
| 14 |
-
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"n_positions": 1024,
|
| 27 |
-
"reorder_and_upcast_attn": false,
|
| 28 |
-
"resid_pdrop": 0.1,
|
| 29 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
-
"scale_attn_weights": true,
|
| 31 |
-
"summary_activation": null,
|
| 32 |
-
"summary_first_dropout": 0.1,
|
| 33 |
-
"summary_proj_to_labels": true,
|
| 34 |
-
"summary_type": "cls_index",
|
| 35 |
-
"summary_use_proj": true,
|
| 36 |
-
"task_specific_params": {
|
| 37 |
-
"text-generation": {
|
| 38 |
-
"do_sample": true,
|
| 39 |
-
"max_length": 50
|
| 40 |
-
}
|
| 41 |
-
},
|
| 42 |
"torch_dtype": "float32",
|
| 43 |
"transformers_version": "4.35.2",
|
| 44 |
"use_cache": true,
|
| 45 |
-
"
|
|
|
|
| 46 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "TinyPixel/pythia-14m",
|
|
|
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": 0.1,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 128,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 512,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 2048,
|
| 17 |
+
"model_type": "gpt_neox",
|
| 18 |
+
"num_attention_heads": 4,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rotary_emb_base": 10000,
|
| 22 |
+
"rotary_pct": 0.25,
|
| 23 |
+
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
"transformers_version": "4.35.2",
|
| 26 |
"use_cache": true,
|
| 27 |
+
"use_parallel_residual": true,
|
| 28 |
+
"vocab_size": 50304
|
| 29 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"eos_token_id":
|
| 5 |
"transformers_version": "4.35.2"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
"transformers_version": "4.35.2"
|
| 6 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f7c5b7adf45a248f75fc03b516ac7d5747b9d080e83198877a8cc78119c30d9
|
| 3 |
+
size 56279344
|