mohamedemam
commited on
Commit
•
cc94e3c
1
Parent(s):
0491bcf
Upload BloomForCausalLM
Browse files- config.json +48 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloomz-7b1",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 32,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 30,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"quantization_config": {
|
25 |
+
"_load_in_4bit": true,
|
26 |
+
"_load_in_8bit": false,
|
27 |
+
"bnb_4bit_compute_dtype": "float16",
|
28 |
+
"bnb_4bit_quant_storage": "uint8",
|
29 |
+
"bnb_4bit_quant_type": "nf4",
|
30 |
+
"bnb_4bit_use_double_quant": false,
|
31 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
32 |
+
"llm_int8_has_fp16_weight": false,
|
33 |
+
"llm_int8_skip_modules": null,
|
34 |
+
"llm_int8_threshold": 6.0,
|
35 |
+
"load_in_4bit": true,
|
36 |
+
"load_in_8bit": false,
|
37 |
+
"quant_method": "bitsandbytes"
|
38 |
+
},
|
39 |
+
"seq_length": 2048,
|
40 |
+
"skip_bias_add": true,
|
41 |
+
"skip_bias_add_qkv": false,
|
42 |
+
"slow_but_exact": false,
|
43 |
+
"torch_dtype": "float16",
|
44 |
+
"transformers_version": "4.42.3",
|
45 |
+
"unk_token_id": 0,
|
46 |
+
"use_cache": false,
|
47 |
+
"vocab_size": 250880
|
48 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d79cff75f0e5343907ec1e1cec5185ac0db5e5f1b29d72981501b7ed59fccad2
|
3 |
+
size 4994038479
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c1d5cd3877c62a1c501d408ced67b8a88751e6d71b7c7d616eaeee573430b00
|
3 |
+
size 587759003
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|