Upload 2 files

.gitattributes

@@ -41,3 +41,4 @@ chk-wikichat-256x28-8590.gguf filter=lfs diff=lfs merge=lfs -text
 ggml-wikichat-256x28-f32-8590.gguf filter=lfs diff=lfs merge=lfs -text
 ggml-wikichat-256x28-f32-9580.gguf filter=lfs diff=lfs merge=lfs -text
 ggml-wikichat-256x28-f32-9590-4k.gguf filter=lfs diff=lfs merge=lfs -text
+chk-wikichat-256x28-9590-4k.gguf filter=lfs diff=lfs merge=lfs -text

chk-wikichat-256x28-9590-4k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e91edc878fa54b434c572e96f7a370e373f98f5105bee73a4704184b6abb68
+size 483790912

model_config_4k.json

@@ -0,0 +1,53 @@
+{
+  "name": "WikiGGML4k",
+  "load_params": {
+    "n_ctx": 4096,
+    "n_batch": 512,
+    "rope_freq_base": 0,
+    "rope_freq_scale": 0,
+    "n_gpu_layers": -1,
+    "use_mlock": true,
+    "main_gpu": 0,
+    "tensor_split": [
+      0
+    ],
+    "seed": -1,
+    "f16_kv": true,
+    "use_mmap": true,
+    "no_kv_offload": false,
+    "num_experts_used": 0
+  },
+  "inference_params": {
+    "n_threads": 4,
+    "n_predict": -1,
+    "top_k": 40,
+    "min_p": 0.05,
+    "top_p": 0.95,
+    "temp": 0.8,
+    "repeat_penalty": 1.1,
+    "input_prefix": "User:",
+    "input_suffix": "\nA:",
+    "antiprompt": [
+      "### Instruction:",
+      "### User:\\n",
+      "User:\\n"
+    ],
+    "pre_prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.",
+    "pre_prompt_suffix": "\\n",
+    "pre_prompt_prefix": "",
+    "seed": -1,
+    "tfs_z": 1,
+    "typical_p": 1,
+    "repeat_last_n": 64,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n_keep": 0,
+    "logit_bias": {},
+    "mirostat": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "memory_f16": true,
+    "multiline_input": false,
+    "penalize_nl": true
+  }
+}