Update models

.gitattributes

@@ -33,3 +33,16 @@ 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-3.2-1B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-1B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbccffcba1e679d2fb906a55b5d6d641aa21bff9ee20fe30cef6dd6b9f8e410
+size 580874080

Llama-3.2-1B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89a46e80c150f92bc0d5dfacb069f46770807664340339a22d886031ee06ddc
+size 732524384

Llama-3.2-1B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdd2550b78bdee5653da8f9d07d74faaafd7cc50602eac9107d8f2c60677d24
+size 690843488

Llama-3.2-1B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5363d4847936b37950b1d048199b616b80edd40e78ed15e7b0f2e36c32433b
+size 641691488

Llama-3.2-1B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150e95f201edeaef9b5d37aec70fcee65533ddeca51a4d1092037195f0302f69
+size 770928480

Llama-3.2-1B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95df2f5144fd67bf11421ad59812fbde45a79c90eb49cb5d79e3d7bddaa1331
+size 807694176

Llama-3.2-1B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e256d51eed0799552f91a4fb8f0d05315b3e3dc1cd4499514e7d87a845951c88
+size 775647072

Llama-3.2-1B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922306ce6b89b731d20130c2a5e909be530c5703fd24b26f7d050bad3faf3fc5
+size 892563296

Llama-3.2-1B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd16584b15af8c268ca60454b63b5021b0b2c7edf66cff2b41210a333b2233d
+size 911503200

Llama-3.2-1B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66260aca245c04327590457d52debf378e0fc93b881b2effb71f9a00703a1953
+size 892563296

Llama-3.2-1B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe00ecc20650188a714bf1766cecbd938e6119e9311c8fe91ca3fb5f3246591
+size 1021800288

Llama-3.2-1B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0522ea0da43f9a089b5f2df7699a659cc320a5259c33506c44925fa03232fc
+size 1321082720

Llama-3.2-1B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f33ad43d2b85b908ff06fe7002b69806a57359b9b2617ca27d7bdea428ae146
+size 2479595360

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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,
+  "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": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}