Upload folder using huggingface_hub

config.json

@@ -6,7 +6,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "quantization_config": {
+  "compression_config": {
     "config_groups": {
       "group_0": {
         "input_activations": null,
@@ -28,15 +28,16 @@
       }
     },
     "format": "pack-quantized",
-    "global_compression_ratio": 1.8899784804275277,
+    "global_compression_ratio": 1.883165566487463,
     "ignore": [
       "lm_head"
     ],
-    "quant_method": "compressed-tensors",
+    "kv_cache_scheme": null,
+    "quant_method": "compressed_tensors",
     "quantization_status": "frozen",
     "sparsity_config": {
       "format": "dense",
-      "global_sparsity": 13.864110180811828,
+      "global_sparsity": 0.14355486953221844,
       "registry_requires_subclass": false,
       "sparsity_structure": "unstructured"
     }
@@ -47,6 +48,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
@@ -57,7 +59,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32000
-}
+}

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.44.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456249d063ce70767c9bd2e16f1bca336ee1c14c486a3532e502e831d77c885d
+oid sha256:086986a21cf81dc1feebf9a0df17a49a3928aa987ba57b508b5c6a129ff3771e
 size 761968600

recipe.yaml

@@ -1,9 +1,8 @@
 quant_stage:
   quant_modifiers:
     GPTQModifier:
-      sequential_update: false
       ignore: [lm_head]
       config_groups:
         group_0:
-          weights: {num_bits: 4, type: int, symmetric: true, strategy: group, group_size: 128}
+          weights: {num_bits: 4, strategy: group, group_size: 128}
           targets: [Linear]

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",