Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 mistral-7b-instruct-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 mistral-7b-instruct-v0.3.bf16.gguf filter=lfs diff=lfs merge=lfs -text
+mistral-7b-instruct-v0.3.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,7 @@
 ---
 license: apache-2.0
-tags:
-- autoquant
-- gguf
-extra_gated_description: If you want to learn more about how we process your personal
-  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+base_model: mistralai/Mistral-7B-v0.3
+extra_gated_description: If you want to learn more about how we process your personal data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
 ---
 
 # Model Card for Mistral-7B-Instruct-v0.3
@@ -162,18 +159,19 @@ def get_current_weather(location: str, format: str):
 conversation = [{"role": "user", "content": "What's the weather like in Paris?"}]
 tools = [get_current_weather]
 
-# render the tool use prompt as a string:
-tool_use_prompt = tokenizer.apply_chat_template(
+
+# format and tokenize the tool use prompt 
+inputs = tokenizer.apply_chat_template(
             conversation,
             tools=tools,
-            tokenize=False,
             add_generation_prompt=True,
+            return_dict=True,
+            return_tensors="pt",
 )
 
-inputs = tokenizer(tool_use_prompt, return_tensors="pt")
-
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
 
+inputs.to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=1000)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```

mistral-7b-instruct-v0.3.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad285df95654b1b5b5cfe8d841b9ffbffb6dd35cb40b9764f2afa06df8d953cb
+size 4557889472

mistral-7b-instruct-v0.3.bf16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f828be62045c220ebdce81502c6f7738de089fde094ba7a4a0de80c362279b3
-size 14497341056
+oid sha256:c0f44c427ef088acf4c52eab0034e47624e7fe8c0c3eda66c46102a3feba8894
+size 14497341376