Delete config.json
Browse files- config.json +0 -46
config.json
DELETED
|
@@ -1,46 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"MicroDistilleryBigramForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"model_type": "custom",
|
| 6 |
-
"custom_model_type": "micro-distillery-bigram",
|
| 7 |
-
"vocab_size": 256,
|
| 8 |
-
"max_position_embeddings": 1024,
|
| 9 |
-
"hidden_size": 512,
|
| 10 |
-
"num_hidden_layers": 0,
|
| 11 |
-
"num_attention_heads": 0,
|
| 12 |
-
"intermediate_size": 0,
|
| 13 |
-
"activation_function": "gelu_new",
|
| 14 |
-
"layer_norm_epsilon": 0.00001,
|
| 15 |
-
"use_cache": true,
|
| 16 |
-
"bos_token_id": 0,
|
| 17 |
-
"eos_token_id": 1,
|
| 18 |
-
"transformers_version": "4.44.0",
|
| 19 |
-
"library_name": "micro-distillery",
|
| 20 |
-
"micro_distillery": {
|
| 21 |
-
"format": "bigram-distilled",
|
| 22 |
-
"dialect": "character-level",
|
| 23 |
-
"reference_arch": "tiny-bigram",
|
| 24 |
-
"distill_from": [
|
| 25 |
-
"smollm2-135m",
|
| 26 |
-
"qwen2.5-0.5b",
|
| 27 |
-
"olmo2-1b",
|
| 28 |
-
"tinyllama-1.1b"
|
| 29 |
-
],
|
| 30 |
-
"harmonic_seed": 1251963776,
|
| 31 |
-
"harmonic_frequencies": [
|
| 32 |
-
1,
|
| 33 |
-
1.618033988749895,
|
| 34 |
-
2,
|
| 35 |
-
3.141592653589793
|
| 36 |
-
],
|
| 37 |
-
"grpo_config": {
|
| 38 |
-
"group_size": 8,
|
| 39 |
-
"kl_penalty": 0.1
|
| 40 |
-
},
|
| 41 |
-
"vae_config": {
|
| 42 |
-
"latent_dim": 32,
|
| 43 |
-
"filter_threshold": 0.7
|
| 44 |
-
}
|
| 45 |
-
}
|
| 46 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|