Trained with Unsloth - config
Browse files- config.json +27 -58
config.json
CHANGED
|
@@ -1,70 +1,39 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"torch_dtype": "float16",
|
| 8 |
-
"eos_token_id":
|
| 9 |
-
"head_dim":
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
-
"
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention"
|
| 51 |
-
],
|
| 52 |
-
"max_position_embeddings": 262144,
|
| 53 |
-
"max_window_layers": 36,
|
| 54 |
-
"model_type": "qwen3",
|
| 55 |
-
"num_attention_heads": 32,
|
| 56 |
-
"num_hidden_layers": 36,
|
| 57 |
-
"num_key_value_heads": 8,
|
| 58 |
-
"pad_token_id": 151654,
|
| 59 |
-
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
-
"rope_theta":
|
| 62 |
-
"sliding_window": null,
|
| 63 |
"tie_word_embeddings": true,
|
| 64 |
-
"
|
| 65 |
-
|
| 66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"use_cache": true,
|
| 68 |
-
"
|
| 69 |
-
"vocab_size": 151936
|
| 70 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
"torch_dtype": "float16",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 960,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2560,
|
| 15 |
+
"is_llama_config": true,
|
| 16 |
+
"max_position_embeddings": 8192,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"num_attention_heads": 15,
|
| 20 |
+
"num_hidden_layers": 32,
|
| 21 |
+
"num_key_value_heads": 5,
|
| 22 |
+
"pad_token_id": 49152,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_interleaved": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 100000,
|
|
|
|
| 28 |
"tie_word_embeddings": true,
|
| 29 |
+
"transformers.js_config": {
|
| 30 |
+
"kv_cache_dtype": {
|
| 31 |
+
"fp16": "float16",
|
| 32 |
+
"q4f16": "float16"
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"transformers_version": "4.57.1",
|
| 36 |
+
"unsloth_version": "2025.10.6",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 49153
|
|
|
|
| 39 |
}
|