Upload folder using huggingface_hub

README.md

@@ -0,0 +1,21 @@
+---
+base_model:
+- medmekk/testing_repo_name
+---
+
+# medmekk/testing_repo_name (Quantized)
+
+## Description
+This model is a quantized version of the original model `medmekk/testing_repo_name`. It has been quantized using int4_weight_only quantization with torchao.
+
+## Quantization Details
+- **Quantization Type**: int4_weight_only
+- **Group Size**: 128
+
+## Usage
+You can use this model in your applications by loading it directly from the Hugging Face Hub:
+
+```python
+from transformers import AutoModel
+
+model = AutoModel.from_pretrained("medmekk/testing_repo_name")

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "modules_to_not_convert": null,
+    "quant_method": "torchao",
+    "quant_type": "int4_weight_only",
+    "quant_type_kwargs": {
+      "group_size": 128
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859b700ec5260a6b232882e8cbdd6d66446ceab6352b82be5b24ddff466467e5
+size 4759189518