Upload MegaForCausalLM
Browse files- config.json +48 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pszemraj/mega-ar-126m-v13-dolma-500k-medium-knowledge-inoc-concat-v1-vN",
|
| 3 |
+
"activation": "silu",
|
| 4 |
+
"add_lm_hidden_dense_layer": false,
|
| 5 |
+
"add_token_type_embeddings": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MegaForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_activation": "softmax",
|
| 10 |
+
"attention_probs_dropout_prob": 0,
|
| 11 |
+
"bidirectional": false,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"chunk_size": -1,
|
| 14 |
+
"classifier_dropout": null,
|
| 15 |
+
"dropout_prob": 0,
|
| 16 |
+
"ema_beta_range": 0.02,
|
| 17 |
+
"ema_delta_alpha_range": 0.2,
|
| 18 |
+
"ema_gamma_omega_range": 1.0,
|
| 19 |
+
"ema_projection_size": 16,
|
| 20 |
+
"eos_token_id": 0,
|
| 21 |
+
"hidden_dropout_prob": 0,
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1536,
|
| 25 |
+
"is_decoder": true,
|
| 26 |
+
"max_positions": 4096,
|
| 27 |
+
"model_type": "mega",
|
| 28 |
+
"nffn_activation_dropout_prob": 0,
|
| 29 |
+
"nffn_hidden_size": 1536,
|
| 30 |
+
"norm_affine": true,
|
| 31 |
+
"normalization_type": "layernorm",
|
| 32 |
+
"normalize_before_ffn": true,
|
| 33 |
+
"normalize_before_mega": true,
|
| 34 |
+
"num_attention_heads": 1,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": null,
|
| 37 |
+
"relative_positional_bias": "rotary",
|
| 38 |
+
"shared_representation_size": 192,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.36.2",
|
| 41 |
+
"truncation": null,
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"use_chunking": false,
|
| 45 |
+
"use_feature_dropout": false,
|
| 46 |
+
"use_normalized_ffn": true,
|
| 47 |
+
"vocab_size": 50304
|
| 48 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.36.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6797e3725f934e91332190eb2b9765e4137041f61c8276ca2d071b245a0c2215
|
| 3 |
+
size 504560824
|