Instructions to use quinnlue/pythia-160-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quinnlue/pythia-160-test with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("quinnlue/pythia-160-test") model = AutoModel.from_pretrained("quinnlue/pythia-160-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +31 -31
- generation_config.json +6 -6
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,31 +1,31 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"MyModel"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": true,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
-
"classifier_dropout": 0.1,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"eos_token_id": 0,
|
| 11 |
-
"hidden_act": "gelu",
|
| 12 |
-
"hidden_dropout": 0.0,
|
| 13 |
-
"hidden_size": 768,
|
| 14 |
-
"initializer_range": 0.02,
|
| 15 |
-
"intermediate_size": 3072,
|
| 16 |
-
"layer_norm_eps": 1e-05,
|
| 17 |
-
"max_position_embeddings": 2048,
|
| 18 |
-
"model_type": "gpt_neox",
|
| 19 |
-
"num_attention_heads": 12,
|
| 20 |
-
"num_hidden_layers": 12,
|
| 21 |
-
"partial_rotary_factor": 0.25,
|
| 22 |
-
"rope_scaling": null,
|
| 23 |
-
"rope_theta": 10000,
|
| 24 |
-
"rotary_emb_base": 10000,
|
| 25 |
-
"rotary_pct": 0.25,
|
| 26 |
-
"tie_word_embeddings": false,
|
| 27 |
-
"transformers_version": "4.57.
|
| 28 |
-
"use_cache": true,
|
| 29 |
-
"use_parallel_residual": true,
|
| 30 |
-
"vocab_size": 50304
|
| 31 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MyModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": 0.1,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"partial_rotary_factor": 0.25,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000,
|
| 24 |
+
"rotary_emb_base": 10000,
|
| 25 |
+
"rotary_pct": 0.25,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"transformers_version": "4.57.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"use_parallel_residual": true,
|
| 30 |
+
"vocab_size": 50304
|
| 31 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 0,
|
| 4 |
-
"eos_token_id": 0,
|
| 5 |
-
"transformers_version": "4.57.
|
| 6 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.57.1"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e971dec35a9a845cabe1b908ec39575f6aa9a186b80d28a98b2e05e301c53e9
|
| 3 |
+
size 762789176
|