asas-ai
/

bloom_3b_int8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

eaalghamdi commited on Aug 21, 2023

Commit

9a74992

•

1 Parent(s): 5a46a07

Upload BloomForCausalLM

Files changed (2) hide show

config.json +5 -5
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bigscience/bloom-3b",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomForCausalLM"
@@ -10,17 +10,17 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_dropout": 0.0,
-  "hidden_size": 2560,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
-  "n_head": 32,
   "n_inner": null,
-  "n_layer": 30,
   "offset_alibi": 100,
   "pad_token_id": 3,
-  "pretraining_tp": 4,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_type": "fp4",

 {
+  "_name_or_path": "bigscience/bloom-560m",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomForCausalLM"
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
+  "n_head": 16,
   "n_inner": null,
+  "n_layer": 24,
   "offset_alibi": 100,
   "pad_token_id": 3,
+  "pretraining_tp": 1,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_type": "fp4",

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94bc1439554be4c42b8dce293b78caa786ddcd07591aabe9f4d72a5c28d1499
-size 3648747617

 version https://git-lfs.github.com/spec/v1
+oid sha256:e4a31b64a6600f1f30371eb06223111d48aaa257b16acfa6c1bf5275fee0b683
+size 817455457