Hugging Face's logo

mmnga
/
cyberagent-calm2-7b-chat-GPTQ-calib-ja-1k

Text Generation
Transformers
llama
Inference Endpoints
text-generation-inference
Model card Files Community
2
mmnga commited on
Commit
2ef45e5
•
1 Parent(s): 2138041

Upload of AutoGPTQ quantized model

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. gptq_model-4bit-128g.safetensors +2 -2
  3. tokenizer.json +1 -6
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "rope_scaling": null,
22
  "rope_theta": 500000,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
  "transformers_version": "4.34.1",
26
  "use_cache": true,
27
  "vocab_size": 65024
 
21
  "rope_scaling": null,
22
  "rope_theta": 500000,
23
  "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
  "transformers_version": "4.34.1",
26
  "use_cache": true,
27
  "vocab_size": 65024
gptq_model-4bit-128g.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5476dcd83439ca695c3fc0102ea87bd2fc61035ac4b581446f0feb9209149e18
3
- size 4437779944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dbb1e500b57e5939a4120595d1a37d53ba23b3af3ba13b0f85c236a664d001f
3
+ size 4437780008
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 2048,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {