Text Generation
Transformers
Safetensors
PyTorch
English
gpt_neox
causal-lm
pythia
safety
unlearning
data-filtering
interpretability
pretraining
eleutherai
gpt-neox
wmdp
cbrn
tamper-resistance
research
model-suite
6.9b
circuit-breaking
knowledge-filtering
open-weight
biothreat
safety-research
model-diffing
training-dynamics
text-generation-inference
Upload GPTNeoXForCausalLM
Browse files- config.json +3 -2
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/checkpoints/hf_checkpoints/annealing_baseline/global_step11921",
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
@@ -18,12 +17,14 @@
|
|
| 18 |
"model_type": "gpt_neox",
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 32,
|
|
|
|
| 21 |
"rope_scaling": null,
|
|
|
|
| 22 |
"rotary_emb_base": 10000.0,
|
| 23 |
"rotary_pct": 0.25,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"use_cache": true,
|
| 28 |
"use_parallel_residual": true,
|
| 29 |
"vocab_size": 50304
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"GPTNeoXForCausalLM"
|
| 4 |
],
|
|
|
|
| 17 |
"model_type": "gpt_neox",
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
"num_hidden_layers": 32,
|
| 20 |
+
"partial_rotary_factor": 0.25,
|
| 21 |
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
"rotary_emb_base": 10000.0,
|
| 24 |
"rotary_pct": 0.25,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.52.4",
|
| 28 |
"use_cache": true,
|
| 29 |
"use_parallel_residual": true,
|
| 30 |
"vocab_size": 50304
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.52.4"
|
| 6 |
}
|