Upload folder using huggingface_hub

README.md

@@ -0,0 +1,23 @@
+---
+base_model:
+- medmekk/Llama-3.3-70B-Instruct-BNB-INT4
+---
+
+# medmekk/Llama-3.3-70B-Instruct-BNB-INT4 (Quantized)
+
+## Description
+This model is a quantized version of the original model `medmekk/Llama-3.3-70B-Instruct-BNB-INT4`. It has been quantized using int4 quantization with bitsandbytes.
+
+## Quantization Details
+- **Quantization Type**: int4
+- **bnb_4bit_quant_type**: fp4
+- **bnb_4bit_use_double_quant**: False
+- **bnb_4bit_compute_dtype**: float32
+- **bnb_4bit_quant_storage**: uint8
+
+## 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/Llama-3.3-70B-Instruct-BNB-INT4")

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f157482e4e762d7eeed4fe1748243cc7cca51016d770856dc87f27f19aee4e
+size 4989348020

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbb4a7499922947099c7ba87ee22a4d426ed34d0418ea079deee4b2991ee600
+size 4898273256

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b03d3f67b89fc2c72d2bd6602535a45b08555da7ad35a0855f9327b152e1484
+size 4945457462

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73815eafb85f2841db0c941a303a2f046ace29fbcd9f9e412bbe1072c3d7c3a
+size 4945457454

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228bfa8560d476000bf1c14b4c9ed2800b0f249125e6e315a67947a3d1d67ec7
+size 4992678209

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075e5aa70e073d356a07e665ac1f9e5db1ad3f2e7474656517b11850449149e5
+size 4983206815

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb60decb404ba0a741c9ae8ed795ac6a4cf61709a70780c8f4f3b6b4780000f
+size 4945457454

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9167fec454cb2da31e446c43fe22ce0d6835291a5c8c3ab03f49f6f953640e00
+size 4992678209

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06baff3f50a79729a6aa4d10a62ad0533ec68c7a34ef9c73d46e4c44481cad9e
+size 915495921