Add model files

.gitattributes

@@ -33,3 +33,9 @@ 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
+LaMini-Flan-T5-248M-candle-q2k.gguf filter=lfs diff=lfs merge=lfs -text
+LaMini-Flan-T5-248M-candle-q3k.gguf filter=lfs diff=lfs merge=lfs -text
+LaMini-Flan-T5-248M-candle-q4k.gguf filter=lfs diff=lfs merge=lfs -text
+LaMini-Flan-T5-248M-candle-q5k.gguf filter=lfs diff=lfs merge=lfs -text
+LaMini-Flan-T5-248M-candle-q6k.gguf filter=lfs diff=lfs merge=lfs -text
+LaMini-Flan-T5-248M-candle-q8k.gguf filter=lfs diff=lfs merge=lfs -text

LaMini-Flan-T5-248M-candle-q2k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373310789ec5f36ec6c17a42d0216d17a0d5070042c85873d0d324ecd2f6dfe7
+size 81437984

LaMini-Flan-T5-248M-candle-q3k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7083b26d89248d615e8cc42b103d74598f23505e455e89daa19045482b4a715f
+size 106577696

LaMini-Flan-T5-248M-candle-q4k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a463a9479c4d7a4dbcf71a18cd8394703be15da42bbcf2c40df1d6a71885f7
+size 139452704

LaMini-Flan-T5-248M-candle-q5k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d8a5123d4c41154341fec57debc9bd4c9c60393d3b65f31dd92a14e0c2b1fe
+size 170393888

LaMini-Flan-T5-248M-candle-q6k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7370c32728c9b97b4069cd7378f5a8455e8ba0b45d930313c77cae163b528bcc
+size 203268896

LaMini-Flan-T5-248M-candle-q8k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0416d4fc47fbfbd806189b0da375125f1a78f6d38ec0deaa0281106d74ab497e
+size 282555680

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}