vivekraina commited on
Commit
82016c6
1 Parent(s): fa6b5da

Upload RWForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +40 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "RWForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
11
+ "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
12
+ },
13
+ "bias": false,
14
+ "bos_token_id": 11,
15
+ "eos_token_id": 11,
16
+ "hidden_dropout": 0.0,
17
+ "hidden_size": 4544,
18
+ "initializer_range": 0.02,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "RefinedWebModel",
21
+ "multi_query": true,
22
+ "n_head": 71,
23
+ "n_layer": 32,
24
+ "parallel_attn": true,
25
+ "quantization_config": {
26
+ "bnb_4bit_compute_dtype": "float32",
27
+ "bnb_4bit_quant_type": "fp4",
28
+ "bnb_4bit_use_double_quant": false,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": false,
34
+ "load_in_8bit": true
35
+ },
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.31.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 65024
40
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.31.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fe7a37b11d8bd9d80fb6c89f74f8154045f91891941123aec4c7b29ba2eb7f
3
+ size 7221688297