nazimali
/

mistral-7b-v0.3-instruct-arabic

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

nazimali commited on Sep 30

Commit

934af36

•

1 Parent(s): 2d42164

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -37,14 +37,14 @@ inference_prompt = """فيما يلي تعليمات تصف مهمة. اكتب
 llm = Llama.from_pretrained(
 	repo_id="nazimali/mistral-7b-v0.3-instruct-arabic",
-	filename="Q8_0.gguf",
 )
 llm.create_chat_completion(
 	messages = [
 		{
 			"role": "user",
-			"content": inference_prompt.format("السلام عليكم، هيا نموء")
 		}
 	]
 )
@@ -55,8 +55,8 @@ llm.create_chat_completion(
 ```shell
 ./llama-cli \
   --hf-repo "nazimali/mistral-7b-v0.3-instruct-arabic" \
-  --hf-file Q8_0.gguf \
-  -p "السلام عليكم، هيا نموء" \
   --conversation
 ```

 llm = Llama.from_pretrained(
 	repo_id="nazimali/mistral-7b-v0.3-instruct-arabic",
+	filename="Q4_K_M.gguf",
 )
 llm.create_chat_completion(
 	messages = [
 		{
 			"role": "user",
+			"content": inference_prompt.format("السلام عليكم كيف حالك؟")
 		}
 	]
 )
 ```shell
 ./llama-cli \
   --hf-repo "nazimali/mistral-7b-v0.3-instruct-arabic" \
+  --hf-file Q4_K_M.gguf \
+  -p "السلام عليكم كيف حالك؟" \
   --conversation
 ```