Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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_8b_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama_3_8b_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama_3_8b_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "eos_token_id": 128009,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": true,
+    "vocab_size": 128256
+}

llama_3_8b_Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c42b5b9675e11849db0436f2c48c00f297b7bb05931bab179556c0304bc230
+size 3179131552

llama_3_8b_Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6ef4c087ce4eb761201e55208c5e857a60c57be4d27122cf96a031c9c25bb0
+size 4920734368

llama_3_8b_Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6919cfc8e6f9321700bedf69d3ce15277a8f4a39f074a3c70c7c51444aa16e29
+size 8540770976