Add models

Signed-off-by: Xin Liu <[email protected]>

Llama-3-8B-Instruct-262k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09e5d2f78bdb4474fa53a78c7bf3cd26e6a8cd59e90913fd95132dd6fd0dfad
+size 3179131104

Llama-3-8B-Instruct-262k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962f1a027f2fad2cbf2a3467e7c2e90bf563d59a6df14d1b291f63bb6d3e39fb
+size 4321956064

Llama-3-8B-Instruct-262k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf07833936ee363300c0782c8d465c44558df41158eadf24d64e82b82a1861a
+size 4018917600

Llama-3-8B-Instruct-262k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae28f9a2908b5e980c41b70ccf7d65011aafbc5aaa852c4a37cec300e8d4239
+size 3664498912

Llama-3-8B-Instruct-262k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6942d6c73a414df73935b29d069418620e99246ab4efb51b5ade8f348aaae5
+size 4661211360

Llama-3-8B-Instruct-262k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493ce3a6d292d9f4386a20ebd31779a89f7bce9e601341d94d92162cd35b95d5
+size 4920733920

Llama-3-8B-Instruct-262k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f426e7ad648c8fecc66c058146ccece1a6351277cbf6ec1c73f524b9c88fd2d3
+size 4692668640

Llama-3-8B-Instruct-262k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d59378f3862f2a0f390caf72d84799ca76f4874dde97feee3f616e81a0d1769
+size 5599293664

Llama-3-8B-Instruct-262k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807ea6d90a9f66a2acd3d0dd668fd71e2db8c1df5db8483d89b3fadde8296a45
+size 5599293664

Llama-3-8B-Instruct-262k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05c7911f6f1952e9df84cca53e6b964dd096a3d4883cee46910a8c76ceff62b
+size 6596006112

Llama-3-8B-Instruct-262k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f310759f6a6f7cfa264062abb03737603095dceefd42ed3286d707a25362988
+size 8540770528

Llama-3-8B-Instruct-262k-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7012103697b68b1f9f10932838ca2c062cebaa5e63b9098ab15acb77454b52
+size 16068890816

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "gradientai/Llama-3-8B-Instruct-262k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 262144,
+  "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": 207112184.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}