Upload GPTBigCodeForCausalLM
Browse files- config.json +29 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ibm-granite/granite-20b-code-instruct",
|
3 |
+
"activation_function": "gelu_pytorch_tanh",
|
4 |
+
"architectures": [
|
5 |
+
"GPTBigCodeForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_softmax_in_fp32": true,
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt_bigcode",
|
15 |
+
"multi_query": true,
|
16 |
+
"n_embd": 6144,
|
17 |
+
"n_head": 48,
|
18 |
+
"n_inner": 24576,
|
19 |
+
"n_layer": 52,
|
20 |
+
"n_positions": 8192,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attention_softmax_in_fp32": true,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.42.3",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 49152
|
29 |
+
}
|
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": "4.42.3"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c626d329b036213bebae4956e661a2b2e844bd1d5dc1595f5e6b344a2a4ba57
|
3 |
+
size 40134054216
|