andersonjas commited on
Commit
ef4c03b
1 Parent(s): 6697b0d

Upload LlamaForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +2 -2
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "chat_summarizer/quantized_8bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -18,7 +18,7 @@
18
  "pretraining_tp": 1,
19
  "quantization_config": {
20
  "batch_size": 1,
21
- "bits": 8,
22
  "block_name_to_quantize": "model.layers",
23
  "damp_percent": 0.1,
24
  "dataset": [
 
1
  {
2
+ "_name_or_path": "work_for_2023_11_10/quantized_8bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
18
  "pretraining_tp": 1,
19
  "quantization_config": {
20
  "batch_size": 1,
21
+ "bits": 4,
22
  "block_name_to_quantize": "model.layers",
23
  "damp_percent": 0.1,
24
  "dataset": [
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df7887db21bb240dfdfcf233a2f61135a94f97754f793cfffdee3465a0658caf
3
- size 7160285785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86d7b9e7286844b478926fa53504956589a8374d5eebb64f6dbf1ca3b8e2137
3
+ size 3896979857