Upload folder using huggingface_hub

compress_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": -1,
+  "sparsity": 0.5,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "lossless": "gdeflate",
+  "prunen": 2,
+  "prunem": 4,
+  "block_size": 128
+}

compressed_modules.json

@@ -0,0 +1 @@
+["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"]

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

deltazip-compressed.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67fba9b0188e12920f1265d796c72e727440e46d5594c5dfd4e05418dd7deec
+size 2956123720