Upload RWForCausalLM
Browse files- config.json +29 -0
- generation_config.json +12 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiiuae/falcon-7b-instruct",
|
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": 1136,
|
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": 8,
|
24 |
+
"parallel_attn": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.32.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 65024
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 11,
|
4 |
+
"do_sample": true,
|
5 |
+
"eod_token_id": 11,
|
6 |
+
"eos_token_id": 11,
|
7 |
+
"max_new_tokens": 200,
|
8 |
+
"pad_token_id": 11,
|
9 |
+
"temperature": 0.7,
|
10 |
+
"top_p": 0.7,
|
11 |
+
"transformers_version": "4.32.0"
|
12 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3e827f6e0b311d5333aea6ed906e7dc0441043082eaa2479913ab6b04a81534
|
3 |
+
size 709689930
|