basiliskinstitute commited on
Commit
7fa19d7
1 Parent(s): b76af8c

Upload 3 files

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/openerotica_Llama-3-lima-nsfw-16k-test",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128256,
9
+ "eos_token_id": 128257,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bits": 4,
22
+ "checkpoint_format": "gptq",
23
+ "damp_percent": 0.1,
24
+ "desc_act": true,
25
+ "group_size": 128,
26
+ "model_file_base_name": null,
27
+ "model_name_or_path": null,
28
+ "quant_method": "gptq",
29
+ "static_groups": false,
30
+ "sym": true,
31
+ "true_sequential": true
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "factor": 2.0,
36
+ "type": "linear"
37
+ },
38
+ "rope_theta": 500000.0,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.40.2",
42
+ "use_cache": false,
43
+ "vocab_size": 128260
44
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5c82c71a55347987a6fb4ff3d60e5fd7deb39933e3fe659e5aa954dec42172
3
+ size 5733009320
quantize_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.1,
5
+ "desc_act": true,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": null,
10
+ "model_file_base_name": null,
11
+ "quant_method": "gptq",
12
+ "checkpoint_format": "gptq"
13
+ }