Add models

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

.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
+*.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-Gradient-1048k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef6124aa67cded967ef545c020bebfc13b7e8931f0423cae06b7491d4c4c06a
+size 3179131136

Llama-3-8B-Instruct-Gradient-1048k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a808b91cde6d819a75e7e3bb07fad87a376521495d3f9335901c4997f454eef8
+size 4321956096

Llama-3-8B-Instruct-Gradient-1048k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdacad367d2d172f405328ddfa4db5ae5311320f8034bbbe4a568d919aaba4c9
+size 4018917632

Llama-3-8B-Instruct-Gradient-1048k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d804260111d0408e1959d41da9b5ffeeabbca03c9a2468eee1da6940190518ed
+size 3664498944

Llama-3-8B-Instruct-Gradient-1048k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054d5fb734a9c9040e37dae466cd485040d352eb743aea22e34129dcc14b2278
+size 4661211392

Llama-3-8B-Instruct-Gradient-1048k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6c81ab41d9873839d444f64893ccce01606473642b7d3fef3e5850bda21264
+size 4920733952

Llama-3-8B-Instruct-Gradient-1048k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13111f10bb4ceca3fb69098444d5715a6324023d6b18bceefac2e8ceec097f4
+size 4692668672

Llama-3-8B-Instruct-Gradient-1048k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e29aa74d7baa6fe0e80f7ab6bd14f85ccacc5d2fd2cea5779a17e785db1eae4
+size 5599293696

Llama-3-8B-Instruct-Gradient-1048k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d7a76d6d723792e77c66c814929460f1715aaff324860696d05436b770b929
+size 5732987136

Llama-3-8B-Instruct-Gradient-1048k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39899b28396cf77b165245cc03a8bc5ea5249efe5de8a46ab611aee4b30d806
+size 5599293696

Llama-3-8B-Instruct-Gradient-1048k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4962ed758b314da060bfc65d25aa82bc045e6223f369341b72104c2ccc4e8299
+size 6596006144

Llama-3-8B-Instruct-Gradient-1048k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb42e00debee39850aa512a0c31cd7185b1989dd2a2b16fe9ad9ebe04549cc8
+size 8540770560

Llama-3-8B-Instruct-Gradient-1048k-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73d1fa08a670f08482d8050867af7b63ccf074f70ed8c1c95463c2c6839fe97
+size 16068890816

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "gradientai/llama3-run1-stage524k-fm-v3",
+  "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": 1048576,
+  "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": 2804339835.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}