Upload README.md

README.md

@@ -1,100 +1,76 @@
 ---
-license: apache-2.0
+license: apache-2.0  
+inference: false  
 ---
 
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-**slim-sentiment** is part of the SLIM ("Structured Language Instruction Model") model series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.  
+**slim-sentiment** 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 **sentiment analysis** function calls, generating output consisting of JSON dictionary corresponding to specified keys.  
+slim-sentiment has been fine-tuned for **sentiment analysis** function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:  
 
-Each slim model has a corresponding 'tool' in a separate repository, e.g.,  
+&nbsp;&nbsp;&nbsp;&nbsp;`{"sentiment": ["positive"]}`
 
-[**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool), which a 4-bit quantized gguf version of the model that is intended to be used for inference.  
 
-Inference speed and loading time is much faster with the 'tool' versions of the model.   
+SLIM models are designed to provide a flexible natural language generative model that can be used as part of a multi-step, multi-model LLM-based automation workflow.  
 
-### Model Description
+Each slim model has a 'quantized tool' version, e.g.,  [**'slim-sentiment-tool'**](https://huggingface.co/llmware/slim-sentiment-tool).  
 
-<!-- Provide a longer summary of what this model is. -->
 
-- **Developed by:** llmware
-- **Model type:** Small, specialized LLM
-- **Language(s) (NLP):** English
-- **License:** Apache 2.0
-- **Finetuned from model:** Tiny Llama 1B
+## Prompt format:
 
-## Uses
+`function = "classify"`  
+`params = "sentiment"`  
+`prompt = "<human> " + {text} + "\n" + `  
+&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`  
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-The intended use of SLIM models is to re-imagine traditional 'hard-coded' classifiers through the use of function calls.  
+<details>
+<summary>Transformers Script </summary>
 
-Example:
-
-    text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."   
-
-    model generation - {"sentiment": ["negative"]}
-
-    keys = "sentiment"
-
-All of the SLIM models use a novel prompt instruction structured as follows:
-
-    "<human> " + text + "<classify> " + keys + "</classify>" + "/n<bot>: "
-
-
-## How to Get Started with the Model
-
-The fastest way to get started with BLING is through direct import in transformers:
-
-    import ast
-    from transformers import AutoModelForCausalLM, AutoTokenizer
-    
     model = AutoModelForCausalLM.from_pretrained("llmware/slim-sentiment")
     tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sentiment")
 
-    text = "The markets declined for a second straight days on news of disappointing earnings."
-
-    keys = "sentiment"
+    function = "classify"
+    params = "sentiment"
 
-    prompt = "<human>: " + text + "\n" + "<classify> " + keys + "</classify>" + "\n<bot>: "
+    text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."  
+    
+    prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
 
-    #   huggingface standard generation script
     inputs = tokenizer(prompt, return_tensors="pt")
-    start_of_output = len(inputs.input_ids[0])
+    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)
+    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
+    )
 
-    output_only = tokenizer.decode(outputs[0][start_of_output:], skip_special_tokens=True)
+    output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
 
-    print("input text sample - ", text)
-    print("llm_response - ", output_only)
+    print("output only: ", output_only)  
 
-    #   where it gets interesting
+    # here's the fun part
     try:
-        # convert llm response output from string to json
-        output_only = ast.literal_eval(output_only)
-        print("converted to json automatically")
-
-        #   look for the key passed in the prompt as a dictionary entry
-        if keys in output_only:
-            if "negative" in output_only[keys]:
-                print("sentiment appears negative - need to handle ...")
-        else:
-            print("response does not appear to include the designated key - will need to try again.")
-
+        output_only = ast.literal_eval(llm_string_output)
+        print("success - converted to python dictionary automatically")
     except:
-        print("could not convert to json automatically - ", output_only)
-
+        print("fail - could not convert to python dictionary automatically - ", llm_string_output)
    
-## Using as Function Call in LLMWare
+   </details>  
+ 
+<details>  
+
 
-We envision the slim models deployed in a pipeline/workflow/templating framework that handles the prompt packaging more elegantly.  
 
-Check out llmware for one such implementation:  
+    
+<summary>Using as Function Call in LLMWare</summary>
 
     from llmware.models import ModelCatalog
     slim_model = ModelCatalog().load_model("llmware/slim-sentiment")
@@ -102,10 +78,13 @@ Check out llmware for one such implementation:
 
     print("llmware - llm_response: ", response)
 
+</details>  
+
     
 ## Model Card Contact
 
-Darren Oberst & llmware team
+Darren Oberst & llmware team  
 
+[Join us on Discord](https://discord.gg/MhZn5Nc39h)