Upload model
Browse files- config.json +60 -0
- generation_config.json +8 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "AI-Sweden-Models/gpt-sw3-356m-instruct",
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_query_key_layer_scaling": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"initializer_range": 0.01,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"max_length": 2048,
|
| 15 |
+
"model_type": "gpt2",
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": 4096,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 2048,
|
| 21 |
+
"normalize_attention_scores": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"quantization_config": {
|
| 24 |
+
"batch_size": 1,
|
| 25 |
+
"bits": 4,
|
| 26 |
+
"block_name_to_quantize": "transformer.h",
|
| 27 |
+
"damp_percent": 0.1,
|
| 28 |
+
"dataset": "c4",
|
| 29 |
+
"desc_act": false,
|
| 30 |
+
"disable_exllama": true,
|
| 31 |
+
"group_size": 128,
|
| 32 |
+
"max_input_length": null,
|
| 33 |
+
"model_seqlen": 2048,
|
| 34 |
+
"module_name_preceding_first_block": [
|
| 35 |
+
"transformer.wte",
|
| 36 |
+
"transformer.wpe",
|
| 37 |
+
"transformer.drop"
|
| 38 |
+
],
|
| 39 |
+
"pad_token_id": null,
|
| 40 |
+
"quant_method": "gptq",
|
| 41 |
+
"sym": true,
|
| 42 |
+
"tokenizer": null,
|
| 43 |
+
"true_sequential": true,
|
| 44 |
+
"use_cuda_fp16": true
|
| 45 |
+
},
|
| 46 |
+
"reorder_and_upcast_attn": false,
|
| 47 |
+
"resid_pdrop": 0.1,
|
| 48 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 49 |
+
"scale_attn_weights": true,
|
| 50 |
+
"summary_activation": null,
|
| 51 |
+
"summary_first_dropout": 0.1,
|
| 52 |
+
"summary_proj_to_labels": true,
|
| 53 |
+
"summary_type": "cls_index",
|
| 54 |
+
"summary_use_proj": true,
|
| 55 |
+
"tokenizer_class": "GPTSw3Tokenizer",
|
| 56 |
+
"torch_dtype": "float16",
|
| 57 |
+
"transformers_version": "4.34.1",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 64000
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 3,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.34.1"
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d4bd14f3dcc5c663c01fdc1a5ec057995f0eec82980f3b3c10d6612463ff681
|
| 3 |
+
size 293681498
|