Add BERTopic model
#98
by
TerriTuson
- opened
- config.json +15 -30
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
config.json
CHANGED
|
@@ -1,32 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
"eos_token_id": 0,
|
| 15 |
-
"hidden_act": "gelu",
|
| 16 |
-
"hidden_size": 5120,
|
| 17 |
-
"initializer_range": 0.02,
|
| 18 |
-
"intermediate_size": 20480,
|
| 19 |
-
"layer_norm_eps": 1e-05,
|
| 20 |
-
"max_position_embeddings": 2048,
|
| 21 |
-
"model_type": "gpt_neox",
|
| 22 |
-
"num_attention_heads": 40,
|
| 23 |
-
"num_hidden_layers": 36,
|
| 24 |
-
"rotary_emb_base": 10000,
|
| 25 |
-
"rotary_pct": 0.25,
|
| 26 |
-
"tie_word_embeddings": false,
|
| 27 |
-
"torch_dtype": "bfloat16",
|
| 28 |
-
"transformers_version": "4.25.1",
|
| 29 |
-
"use_cache": true,
|
| 30 |
-
"use_parallel_residual": true,
|
| 31 |
-
"vocab_size": 50280
|
| 32 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"calculate_probabilities": false,
|
| 3 |
+
"language": "english",
|
| 4 |
+
"low_memory": false,
|
| 5 |
+
"min_topic_size": 10,
|
| 6 |
+
"n_gram_range": [
|
| 7 |
+
1,
|
| 8 |
+
1
|
| 9 |
],
|
| 10 |
+
"nr_topics": null,
|
| 11 |
+
"seed_topic_list": null,
|
| 12 |
+
"top_n_words": 10,
|
| 13 |
+
"verbose": true,
|
| 14 |
+
"zeroshot_min_similarity": 0.7,
|
| 15 |
+
"zeroshot_topic_list": null,
|
| 16 |
+
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
|
| 17 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
topic_embeddings.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46b73da98aeeba43efefffec94f4664aff911433758bbe46fc21a7771ed4ab5c
|
| 3 |
+
size 2004576
|
topics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|