Upload folder using huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+base_model:
+- medmekk/Llama-3.2-1B-ao-int8wo
+---
+# medmekk/Llama-3.2-1B-ao-int8wo (Quantized)
+
+## Description
+This model is a quantized version of the original model [`medmekk/Llama-3.2-1B-ao-int8wo`](https://huggingface.co/medmekk/Llama-3.2-1B-ao-int8wo). 
+
+It's quantized using the TorchAO library using the [torchao-my-repo](https://huggingface.co/spaces/pytorch/torchao-my-repo) space.
+
+## Quantization Details
+- **Quantization Type**: int8_weight_only
+- **Group Size**: None
+

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "modules_to_not_convert": null,
+    "quant_method": "torchao",
+    "quant_type": "int8_weight_only",
+    "quant_type_kwargs": {
+      "group_size": null
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05cc376b89d79361b2722c47ec3690b8c403882e7a9ec692d48f785183a1559
+size 1502450898