Upload README.md

README.md

@@ -1,90 +1,48 @@
 ---
-license: apache-2.0  
-inference: false  
+license: apache-2.0
 ---
 
-# SLIM-TAGS-TOOL
+# SLIM-TOPICS-TOOL
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**slim-tags-tool** is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.  
 
-slim-sentiment has been fine-tuned for **generating relevant extractive summary tags** function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:  
+**slim-topics-tool** is a 4_K_M quantized GGUF version of slim-topics, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.  
 
-&nbsp;&nbsp;&nbsp;&nbsp;`{"tags": ["tag1", "tag2", "tag3", ... ]}`
+[**slim-topics**](https://huggingface.co/llmware/slim-topics) is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.
 
+To pull the model via API:  
 
-SLIM models are designed to generate structured outputs that can be used programmatically as part of a multi-step, multi-model LLM-based automation workflow.  
-
-Each slim model has a 'quantized tool' version, e.g.,  [**'slim-tags-tool'**](https://huggingface.co/llmware/slim-tags-tool).  
-
-
-## Prompt format:
-
-`function = "classify"`  
-`params = "tags"`  
-`prompt = "<human> " + {text} + "\n" + `  
-&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`  
-
-
-<details>
-<summary>Transformers Script </summary>
-
-    model = AutoModelForCausalLM.from_pretrained("llmware/slim-topics")
-    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-topics")
-
-    function = "classify"
-    params = "topic"
-
-    text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."  
+    from huggingface_hub import snapshot_download           
+    snapshot_download("llmware/slim-topics-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)  
     
-    prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
-
-    inputs = tokenizer(prompt, return_tensors="pt")
-    start_of_input = len(inputs.input_ids[0])
 
-    outputs = model.generate(
-        inputs.input_ids.to('cpu'),
-        eos_token_id=tokenizer.eos_token_id,
-        pad_token_id=tokenizer.eos_token_id,
-        do_sample=True,
-        temperature=0.3,
-        max_new_tokens=100
-    )
+Load in your favorite GGUF inference engine, or try with llmware as follows:
 
-    output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
+    from llmware.models import ModelCatalog  
+    
+    # to load the model and make a basic inference
+    model = ModelCatalog().load_model("slim-topics-tool")
+    response = model.function_call(text_sample)  
 
-    print("output only: ", output_only)  
+    # this one line will download the model and run a series of tests
+    ModelCatalog().tool_test_run("slim-topics-tool", verbose=True)  
 
-    # here's the fun part
-    try:
-        output_only = ast.literal_eval(llm_string_output)
-        print("success - converted to python dictionary automatically")
-    except:
-        print("fail - could not convert to python dictionary automatically - ", llm_string_output)
-   
-   </details>  
- 
-<details>  
 
+Slim models can also be loaded even more simply as part of a multi-model, multi-step LLMfx calls:
 
+    from llmware.agents import LLMfx
 
-    
-<summary>Using as Function Call in LLMWare</summary>
+    llm_fx = LLMfx()
+    llm_fx.load_tool("topics")
+    response = llm_fx.topics(text)  
 
-    from llmware.models import ModelCatalog
-    slim_model = ModelCatalog().load_model("llmware/slim-topics")
-    response = slim_model.function_call(text,params=["topics"], function="classify")
 
-    print("llmware - llm_response: ", response)
+Note: please review [**config.json**](https://huggingface.co/llmware/slim-topics-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.  
 
-</details>  
 
-    
 ## Model Card Contact
 
 Darren Oberst & llmware team  
 
-[Join us on Discord](https://discord.gg/MhZn5Nc39h)
-
-
+[Any questions? Join us on Discord](https://discord.gg/MhZn5Nc39h)