Upload folder using huggingface_hub

README.md

@@ -26,30 +26,20 @@ This is a compressed model using [deltazip](https://github.com/eth-easl/deltazip
 #### Prompt: 
 
 ```
-<bos><start_of_turn>user
-Who is Alan Turing?<end_of_turn>
-
+[{'role': 'user', 'content': 'Who is Alan Turing?'}]
 ```
 
 #### Output: 
 
 ```
 <bos><start_of_turn>user
-<bos><start_of_turn>user
-Who is Alan Turing?<end_of_turn><end_of_turn>
-*Alan Turing* (1912-1954) was a British mathematician and computer scientist who is considered the father of theoretical computer science and artificial intelligence. 
-
-Here are some key points about his life and work:
-
-**Early Life and Education:**
-
-* Born in London, England, in 1912.
-* Showed exceptional mathematical ability from a young age.
-* Studied mathematics at King's College, Cambridge.
+Who is Alan Turing?<end_of_turn>
+*Alan Turing* (1912-1954) was a British mathematician and computer scientist who is widely considered to be the father of theoretical computer science and artificial intelligence.
 
-**World War II Contributions:**
+Here are some of his key contributions:
 
-* Played a crucial role in breaking the German Enigma
+* **Turing Machine:** He proposed the concept of a *Turing machine*, a theoretical model of computation that can simulate any algorithm. This laid the foundation for modern computers.
+* **Codebreaking during World War II:** Turing played a crucial role in breaking the German Enigma code at Bletchley Park, significantly contributing to the Allied victory
 ```
 
 ## 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": "google/gemma-2-9b", "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": "google/gemma-2-9b", "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:b36129bbbcee3a1541bc6de060a71e4994ab1fd3b8fcabb4565c876eae268d60
-size 7843907696
+oid sha256:897ba4e703037cc32267c25687fbb307128e3c357d1fa3d7a5e2b7afc434db60
+size 6795122216

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afc4612a55c9c4b6223058eb59ae051813e1a51cb3f95b0f29ad864d50e4781
-size 34362972
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873