Upload config.json with huggingface_hub
Browse files- config.json +44 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "/data-fsx/swiftkv-llama33-70b-pretrain-math-1p5m-prod",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"LlamaSwiftKVForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0,
|
| 9 |
+
"bos_token_id": 128000,
|
| 10 |
+
"eos_token_id": [
|
| 11 |
+
128001,
|
| 12 |
+
128008,
|
| 13 |
+
128009
|
| 14 |
+
],
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 8192,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 28672,
|
| 20 |
+
"key_value_group_size": 1,
|
| 21 |
+
"max_position_embeddings": 131072,
|
| 22 |
+
"mlp_bias": false,
|
| 23 |
+
"model_type": "llama_swiftkv",
|
| 24 |
+
"num_attention_heads": 64,
|
| 25 |
+
"num_hidden_layers": 80,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"num_key_value_layers": 40,
|
| 28 |
+
"pretraining_tp": 1,
|
| 29 |
+
"rms_norm_eps": 1e-05,
|
| 30 |
+
"rope_scaling": {
|
| 31 |
+
"factor": 8,
|
| 32 |
+
"high_freq_factor": 4,
|
| 33 |
+
"low_freq_factor": 1,
|
| 34 |
+
"original_max_position_embeddings": 8192,
|
| 35 |
+
"rope_type": "llama3"
|
| 36 |
+
},
|
| 37 |
+
"rope_theta": 500000,
|
| 38 |
+
"swiftkv": true,
|
| 39 |
+
"tie_word_embeddings": false,
|
| 40 |
+
"torch_dtype": "bfloat16",
|
| 41 |
+
"transformers_version": "4.47.0",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 128256
|
| 44 |
+
}
|