Oliver Holworthy commited on
Remove unused config_vllm.json
Browse files- config_vllm.json +0 -38
config_vllm.json
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "nvidia/llama-3.2-nv-embedqa-1b-v2",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaModel"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id": 128001,
|
| 10 |
-
"head_dim": 64,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2048,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 8192,
|
| 15 |
-
"max_position_embeddings": 131072,
|
| 16 |
-
"is_causal": false,
|
| 17 |
-
"mlp_bias": false,
|
| 18 |
-
"model_type": "llama",
|
| 19 |
-
"num_attention_heads": 32,
|
| 20 |
-
"num_hidden_layers": 16,
|
| 21 |
-
"num_key_value_heads": 8,
|
| 22 |
-
"pooling": "avg",
|
| 23 |
-
"pretraining_tp": 1,
|
| 24 |
-
"rms_norm_eps": 1e-05,
|
| 25 |
-
"rope_scaling": {
|
| 26 |
-
"factor": 32.0,
|
| 27 |
-
"high_freq_factor": 4.0,
|
| 28 |
-
"low_freq_factor": 1.0,
|
| 29 |
-
"original_max_position_embeddings": 8192,
|
| 30 |
-
"rope_type": "llama3"
|
| 31 |
-
},
|
| 32 |
-
"rope_theta": 500000.0,
|
| 33 |
-
"tie_word_embeddings": true,
|
| 34 |
-
"torch_dtype": "bfloat16",
|
| 35 |
-
"transformers_version": "4.44.2",
|
| 36 |
-
"use_cache": true,
|
| 37 |
-
"vocab_size": 128256
|
| 38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|