Hugging Face's logo

Minami-su
/
Qwen1.5-0.5B-Chat_llamafy

Text Generation
Transformers
PyTorch
English
Chinese
llama
qwen
qwen1.5
qwen2
conversational
text-generation-inference
Model card Files Community
1
Minami-su commited on
Commit
4febfcc
•
1 Parent(s): 2f79239

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -38,6 +38,7 @@ generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)
38
 
39
  ## Test
40
  load in 4bit
 
41
  hf-causal (pretrained=Qwen1.5-0.5B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
42
  | Task |Version| Metric |Value | |Stderr|
43
  |-------------|------:|--------|-----:|---|-----:|
@@ -46,7 +47,9 @@ hf-causal (pretrained=Qwen1.5-0.5B-Chat), limit: None, provide_description: Fals
46
  |truthfulqa_mc| 1|mc1 |0.2534|± |0.0152|
47
  | | |mc2 |0.4322|± |0.0151|
48
  |winogrande | 0|acc |0.5564|± |0.0140|
 
49
  load in 4bit
 
50
  hf-causal (pretrained=Qwen1.5-0.5B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
51
  | Task |Version| Metric |Value | |Stderr|
52
  |-------------|------:|--------|-----:|---|-----:|
 
38
 
39
  ## Test
40
  load in 4bit
41
+
42
  hf-causal (pretrained=Qwen1.5-0.5B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
43
  | Task |Version| Metric |Value | |Stderr|
44
  |-------------|------:|--------|-----:|---|-----:|
 
47
  |truthfulqa_mc| 1|mc1 |0.2534|± |0.0152|
48
  | | |mc2 |0.4322|± |0.0151|
49
  |winogrande | 0|acc |0.5564|± |0.0140|
50
+
51
  load in 4bit
52
+
53
  hf-causal (pretrained=Qwen1.5-0.5B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
54
  | Task |Version| Metric |Value | |Stderr|
55
  |-------------|------:|--------|-----:|---|-----:|