add model
Browse files- config.json +43 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hivemind/gpt-j-6B-8bit",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTJForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"eight_bit": true,
|
| 10 |
+
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"gradient_checkpointing": false,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"layer_norm_epsilon": 1e-05,
|
| 15 |
+
"model_type": "gptj",
|
| 16 |
+
"n_embd": 4096,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 28,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"resid_pdrop": 0.0,
|
| 22 |
+
"rotary": true,
|
| 23 |
+
"rotary_dim": 64,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50,
|
| 34 |
+
"temperature": 1.0
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50400
|
| 43 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0b01532712b780072cfd071bf03248bb40969c8bd0d9041fe9dbd4d4be87bea
|
| 3 |
+
size 6212161484
|