Upload folder using huggingface_hub

README.md

@@ -13,8 +13,8 @@ This is [codegen25-7b-multi](https://huggingface.co/Salesforce/codegen25-7b-mult
 
 Weight compression was performed using `nncf.compress_weights` with the following parameters:
 
-* mode: **int4_sym**
-* ratio: **1**
+* mode: **int4_asym**
+* ratio: **0.8**
 * group_size: **128**
 
 For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).

config.json

@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,8 +23,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 51200
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

openvino_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2c0cf67087123f381306eb3a228ec315467752925a7f076d18adeb3beb5cc8
-size 3759460808
+oid sha256:a14a2a2f26ff811c95361a9e3919c27039d78362a07c7eed3e2d1396919692d0
+size 4425597304