Upload folder using huggingface_hub

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

model.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14466f9d658bf4a79f96c3f3f22759707c291cac4e62fea625e80c7d32169991
+size 4368438944

model.yml

@@ -0,0 +1,20 @@
+name: mistral
+model: mistral:7B
+version: 1
+
+files:
+	- llama_model_path: model.gguf
+
+# Results Preferences
+top_p: 0.95
+temperature: 0.7
+frequency_penalty: 0
+presence_penalty: 0
+max_tokens: 4096 # Infer from base config.json -> max_position_embeddings
+stream: true # true | false
+
+# Engine / Model Settings
+ngl: 32 # Infer from base config.json -> num_attention_heads
+ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
+engine: cortex.llamacpp
+prompt_template: "{system_message} [INST] {prompt} [/INST]"