almazrooei33 commited on
Commit
d3de3b3
1 Parent(s): cb96d34

Upload 3 files

Browse files
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "inceptionai/jais-family-30b-16k-chat",
3
+ "activation_function": "swiglu",
4
+ "alibi_scaling": null,
5
+ "architectures": [
6
+ "JAISLMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "inceptionai/jais-family-30b-16k-chat--configuration_jais.JAISConfig",
11
+ "AutoModel": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISModel",
12
+ "AutoModelForCausalLM": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISLMHeadModel",
13
+ "AutoModelForQuestionAnswering": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForSequenceClassification",
15
+ "AutoModelForTokenClassification": "inceptionai/jais-family-30b-16k-chat--modeling_jais.JAISForTokenClassification"
16
+ },
17
+ "bos_token_id": 0,
18
+ "embd_pdrop": 0.0,
19
+ "eos_token_id": 0,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_epsilon": 1e-05,
22
+ "model_type": "jais",
23
+ "mup_embeddings_scale": 14.6,
24
+ "mup_output_alpha": 2.22,
25
+ "mup_scale_qk_dot_by_d": true,
26
+ "mup_width_scale": 0.03571428571428571,
27
+ "n_embd": 7168,
28
+ "n_head": 56,
29
+ "n_inner": 19114,
30
+ "n_layer": 48,
31
+ "n_positions": 16384,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "alibi",
34
+ "quantization_config": {
35
+ "_load_in_4bit": true,
36
+ "_load_in_8bit": false,
37
+ "bnb_4bit_compute_dtype": "bfloat16",
38
+ "bnb_4bit_quant_storage": "uint8",
39
+ "bnb_4bit_quant_type": "nf4",
40
+ "bnb_4bit_use_double_quant": true,
41
+ "llm_int8_enable_fp32_cpu_offload": false,
42
+ "llm_int8_has_fp16_weight": false,
43
+ "llm_int8_skip_modules": null,
44
+ "llm_int8_threshold": 6.0,
45
+ "load_in_4bit": true,
46
+ "load_in_8bit": false,
47
+ "quant_method": "bitsandbytes"
48
+ },
49
+ "reorder_and_upcast_attn": false,
50
+ "resid_pdrop": 0.0,
51
+ "rotary_dim": null,
52
+ "scale_attn_by_inverse_layer_idx": false,
53
+ "scale_attn_weights": true,
54
+ "torch_dtype": "float16",
55
+ "transformers_version": "4.44.0",
56
+ "use_cache": true,
57
+ "vocab_size": 84992
58
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.0"
7
+ }
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff