Upload folder using huggingface_hub

README.md

@@ -26,14 +26,7 @@ This is a compressed model using [deltazip](https://github.com/eth-easl/deltazip
 #### Prompt: 
 
 ```
-<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-
-Cutting Knowledge Date: December 2023
-Today Date: 04 Dec 2024
-
-<|eot_id|><|start_header_id|>user<|end_header_id|>
-
-Who is Alan Turing?<|eot_id|>
+[{'role': 'user', 'content': 'Who is Alan Turing?'}]
 ```
 
 #### Output: 
@@ -42,22 +35,15 @@ Who is Alan Turing?<|eot_id|>
 <|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
 Cutting Knowledge Date: December 2023
-Today Date: 04 Dec 2024
-
-<|eot_id|><|start_header_id|>user<|end_header_id|>
-
-<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-
-Cutting Knowledge Date: December 2023
-Today Date: 04 Dec 2024
+Today Date: 05 Dec 2024
 
 <|eot_id|><|start_header_id|>user<|end_header_id|>
 
-Who is Alan Turing?<|eot_id|><|eot_id|><|start_header_id|>assistant<|end_header_id|>
+Who is Alan Turing?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
 
-Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, and philosopher. He is widely considered one of the most influential figures in the development of computer science and artificial intelligence.
+Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, and philosopher. He is widely regarded as one of the most influential figures in the development of computer science, artificial intelligence, and cryptography.
 
-Turing was born in London, England, and showed exceptional mathematical
+Turing was born in London, England, and studied mathematics at King's College, Cambridge. During World War II, he worked at the Government Code and Cypher School (GC&CS) at
 ```
 
 ## Evaluation

compress_config.json

@@ -4,7 +4,7 @@
   "sparsity": 0.5,
   "damp_percent": 0.01,
   "desc_act": false,
-  "sym": false,
+  "sym": true,
   "true_sequential": true,
   "lossless": "none",
   "prunen": 2,

delta_config.json

@@ -1 +1 @@
-{"base_model": "meta-llama/Llama-3.2-3B", "compress_config": {"bits": 4, "group_size": -1, "sparsity": 0.5, "damp_percent": 0.01, "desc_act": false, "sym": false, "true_sequential": true, "lossless": "none", "prunen": 2, "prunem": 4, "block_size": 128}, "target_modules": ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj", "self_attn.o_proj", "mlp.up_proj", "mlp.gate_proj", "mlp.down_proj"]}
+{"base_model": "meta-llama/Llama-3.2-3B", "compress_config": {"bits": 4, "group_size": -1, "sparsity": 0.5, "damp_percent": 0.01, "desc_act": false, "sym": true, "true_sequential": true, "lossless": "none", "prunen": 2, "prunem": 4, "block_size": 128}, "target_modules": ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj", "self_attn.o_proj", "mlp.up_proj", "mlp.gate_proj", "mlp.down_proj"]}

deltazip-compressed.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61abe929cedc3d1dac377b2ddfdf0f652c1868d701c3ab440bbbdc1bd4895a0b
-size 2990656912
+oid sha256:703a384792cf21021a4f6d089349b07b3eb5aa458443e47c1395e9486d9b6533
+size 2634561712

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384a7e7c676f7be2e5d2e8449c508be9b00e5b18c5b3c39ebc626e96b3f4b988
-size 17210019
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920