Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llama-3.2-3b.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -19,26 +19,11 @@
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "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": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_cache": false,
   "vocab_size": 32000

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.45.2"
 }

llama-3.2-3b.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1905192149c17510065a95767fe62612bfc107e446972d3330a9f23b2a15089
+size 1169808672

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee574faf545fc9712993980637d4be5ceb10bdcc23f7a1e1a294d30bf8417cd7
+oid sha256:d4e2b1bd2872d357d44803b49a175f84fc5bd7bbb810d2a6657c900048514578
 size 2200164718