Upload folder using huggingface_hub

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "./test_llama1.1b_W4A16_group_compressed",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "compression_config": {
+    "quantization_config": {
+      "config_groups": {
+        "group_0": {
+          "input_activations": null,
+          "output_activations": null,
+          "targets": [
+            "Linear"
+          ],
+          "weights": {
+            "block_structure": null,
+            "dynamic": false,
+            "group_size": 128,
+            "num_bits": 4,
+            "observer": "minmax",
+            "observer_kwargs": {},
+            "strategy": "group",
+            "symmetric": true,
+            "type": "int"
+          }
+        }
+      },
+      "format": "pack-quantized",
+      "global_compression_ratio": 2.2202386697247802,
+      "ignore": [
+        "lm_head"
+      ],
+      "quant_method": "sparseml",
+      "quantization_status": "frozen"
+    },
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 13.035292091297688,
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured"
+    }
+  },
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f286cbc2749160a6e609aa5e3dd2546598bf5067f6c64bb66c7f812ddf85364b
+size 1047023664

recipe.yaml

@@ -0,0 +1,8 @@
+test_stage:
+  quant_modifiers:
+    vLLMQuantizationModifier:
+      ignore: [lm_head]
+      config_groups:
+        group_0:
+          weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128}
+          targets: [Linear]

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}