Initial GPTQ model commit
Browse files- config.json +39 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoderplus/large-model",
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTBigCodeForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_softmax_in_fp32": true,
|
| 8 |
+
"multi_query": true,
|
| 9 |
+
"attn_pdrop": 0.1,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"embd_pdrop": 0.1,
|
| 12 |
+
"eos_token_id": 0,
|
| 13 |
+
"inference_runner": 0,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"max_batch_size": null,
|
| 17 |
+
"max_sequence_length": null,
|
| 18 |
+
"model_type": "gpt_bigcode",
|
| 19 |
+
"n_embd": 6144,
|
| 20 |
+
"n_head": 48,
|
| 21 |
+
"n_inner": 24576,
|
| 22 |
+
"n_layer": 40,
|
| 23 |
+
"n_positions": 8192,
|
| 24 |
+
"pad_key_length": true,
|
| 25 |
+
"pre_allocate_kv_cache": false,
|
| 26 |
+
"resid_pdrop": 0.1,
|
| 27 |
+
"scale_attention_softmax_in_fp32": true,
|
| 28 |
+
"scale_attn_weights": true,
|
| 29 |
+
"summary_activation": null,
|
| 30 |
+
"summary_first_dropout": 0.1,
|
| 31 |
+
"summary_proj_to_labels": true,
|
| 32 |
+
"summary_type": "cls_index",
|
| 33 |
+
"summary_use_proj": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.28.1",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"validate_runner_input": true,
|
| 38 |
+
"vocab_size": 49152
|
| 39 |
+
}
|