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
+DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text

DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b1b2b07a9bb8801524701652694d4f273c57761b82be8d31fdfc98cfd264fe
+size 3179133504

DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0312933e1c8e0335f19fb6d2abd160644cbe16877430540c29f1e878845683ed
+size 4321958464

DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed7e9d857c304751bbff087f5d5b311d2b64c864069177dbbe2797847f6ad22
+size 4018920000

DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f438fc4b8c091a1d1ccd0adec4cf70501f4596bc01fd76e103d03e42d62c0ed
+size 3664501312

DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeff9a33ab8ad47a72e10193f5f60f559f6638f68cc61d8d12a6cf6ce6a3e63
+size 4661213760

DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f903c95b79bc959ddc9ddf72622028540948fe8b53a3eb85a3e019a442287d93
+size 4920736320

DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a3b33cd3f933f76d02b736d83af7ea82c38a03b0c978ebc49230dd651d6324
+size 4692671040

DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0ad8d4ab9ef3fffa7e9e3b48e072ac13a612d66f2df5c4c62353d351036350
+size 5599296064

DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9627906af24eeece3929ab7c53fd6846e3dcb2fa9d25a411d1aa26e1fa5bc298
+size 5732989504

DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6e4da9d2cc75acf2a984ee09721b0c4c28b6753387b04f49194db2a5ea37cd
+size 5599296064

DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c2bf9131e7764a365e52614fc4981acbf5ae766e9e60e46c83a3a0f9d15c14
+size 6596008512

DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf976b94cb574b59fd618f1785a44f653b84659173dc258da63d5e2ca7ac038
+size 8540772928

DeepSeek-R1-Distill-Llama-8B-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7889900cea3d7e3f9c71b632ba502d51a27de58fa0fe5804e596ee199c5f28be
+size 16068893248

config.json

@@ -0,0 +1,34 @@
+{
+  "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": 131072,
+  "mlp_bias": false,
+  "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": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}