Sentence Similarity
Transformers
Safetensors
English
llama
feature-extraction
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
text-reranking
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
custom_code
text-generation-inference
Inference Endpoints
Create config.json
Browse files- config.json +31 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaEncoderModel"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoModel": "McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp--modeling_llama_encoder.LlamaEncoderModel"
|
10 |
+
},
|
11 |
+
"bos_token_id": 128000,
|
12 |
+
"eos_token_id": 128001,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 4096,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 14336,
|
17 |
+
"max_position_embeddings": 8192,
|
18 |
+
"model_type": "llama",
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_hidden_layers": 32,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 0.00001,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 500000,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.40.0.dev0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 128256
|
31 |
+
}
|