Hugging Face's logo

HabibAhmed
/
Granite3.2-2B-lora-FP16

PEFT
Safetensors
Model card Files Community
HabibAhmed commited on
Commit
0c3053a
·
verified ·
1 Parent(s): c325a78

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .ipynb_checkpoints/Granite3.2-2B-INT8-lora-FP16-Evaluation_Results-checkpoint.json +34 -0
  2. Granite3.2-2B-INT8-lora-FP16-Evaluation_Results.json +34 -0
  3. Granite3.2-2B-INT8-lora-FP16-Inference_Curve.png +0 -0
  4. Granite3.2-2B-INT8-lora-FP16-Latency_Histogram.png +0 -0
  5. Granite3.2-2B-INT8-lora-FP16-Memory_Histogram.png +0 -0
  6. Granite3.2-2B-INT8-lora-FP16-Memory_Usage_Curve.png +0 -0
.ipynb_checkpoints/Granite3.2-2B-INT8-lora-FP16-Evaluation_Results-checkpoint.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss:": 0.6305108742865526,
3
+ "perplexity:": 1.8785700472923528,
4
+ "performance_metrics:": {
5
+ "accuracy:": 0.9993324432576769,
6
+ "precision:": 1.0,
7
+ "recall:": 1.0,
8
+ "f1:": 1.0,
9
+ "bleu:": 0.9590048346949761,
10
+ "rouge:": {
11
+ "rouge1": 0.9775700757864699,
12
+ "rouge2": 0.9774440683543273,
13
+ "rougeL": 0.9775700757864699
14
+ },
15
+ "semantic_similarity_avg:": 0.9973837733268738
16
+ },
17
+ "mauve:": 0.8771966174300425,
18
+ "inference_performance:": {
19
+ "min_latency_ms": 197.59607315063477,
20
+ "max_latency_ms": 11124.351501464844,
21
+ "lower_quartile_ms": 210.84624528884888,
22
+ "median_latency_ms": 262.72761821746826,
23
+ "upper_quartile_ms": 6509.876728057861,
24
+ "avg_latency_ms": 2794.198556162805,
25
+ "min_memory_gb": 0.04572629928588867,
26
+ "max_memory_gb": 0.8657946586608887,
27
+ "lower_quartile_gb": 0.16850972175598145,
28
+ "median_memory_gb": 0.3102116584777832,
29
+ "upper_quartile_gb": 0.6448842287063599,
30
+ "avg_memory_gb": 0.37839093800380486,
31
+ "model_load_memory_gb": 6.0996575355529785,
32
+ "avg_inference_memory_gb": 0.37839093800380486
33
+ }
34
+ }
Granite3.2-2B-INT8-lora-FP16-Evaluation_Results.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss:": 0.6305108742865526,
3
+ "perplexity:": 1.8785700472923528,
4
+ "performance_metrics:": {
5
+ "accuracy:": 0.9993324432576769,
6
+ "precision:": 1.0,
7
+ "recall:": 1.0,
8
+ "f1:": 1.0,
9
+ "bleu:": 0.9590048346949761,
10
+ "rouge:": {
11
+ "rouge1": 0.9775700757864699,
12
+ "rouge2": 0.9774440683543273,
13
+ "rougeL": 0.9775700757864699
14
+ },
15
+ "semantic_similarity_avg:": 0.9973837733268738
16
+ },
17
+ "mauve:": 0.8771966174300425,
18
+ "inference_performance:": {
19
+ "min_latency_ms": 197.59607315063477,
20
+ "max_latency_ms": 11124.351501464844,
21
+ "lower_quartile_ms": 210.84624528884888,
22
+ "median_latency_ms": 262.72761821746826,
23
+ "upper_quartile_ms": 6509.876728057861,
24
+ "avg_latency_ms": 2794.198556162805,
25
+ "min_memory_gb": 0.04572629928588867,
26
+ "max_memory_gb": 0.8657946586608887,
27
+ "lower_quartile_gb": 0.16850972175598145,
28
+ "median_memory_gb": 0.3102116584777832,
29
+ "upper_quartile_gb": 0.6448842287063599,
30
+ "avg_memory_gb": 0.37839093800380486,
31
+ "model_load_memory_gb": 6.0996575355529785,
32
+ "avg_inference_memory_gb": 0.37839093800380486
33
+ }
34
+ }
Granite3.2-2B-INT8-lora-FP16-Inference_Curve.png ADDED
Granite3.2-2B-INT8-lora-FP16-Latency_Histogram.png ADDED
Granite3.2-2B-INT8-lora-FP16-Memory_Histogram.png ADDED
Granite3.2-2B-INT8-lora-FP16-Memory_Usage_Curve.png ADDED