Update README.md

README.md

@@ -1,11 +1,15 @@
 ---
 library_name: transformers
-tags: []
+license: apache-2.0
+datasets:
+- THUDM/AgentInstruct
+language:
+- en
 ---
 
 # Mistral-7B fine-tuned on AgentInstruct
 
-[Mistral-7b-v1.0]() fine-tuned on the dataset [AgentInstruct] for "*better* acting as an agent"
+[Mistral-7b-v1.0]() fine-tuned on the dataset [AgentInstruct](https://huggingface.co/datasets/THUDM/AgentInstruct) for "*better* acting as an agent"
 
 
 
@@ -53,128 +57,83 @@ AgentInstruct includes 1,866 trajectories from
 stands for filtered trajectories. 
 
 ## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure 
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-
-
+TBD
+
+## Example of usage
+
+```py
+from transformers import AutoTokenizer, AutoModelForCausalLM, StoppingCriteria
+
+tokenizer = AutoTokenizer.from_pretrained("mrm8488/mistral-7b-ft-AgentInstruct")
+model = AutoModelForCausalLM.from_pretrained("mrm8488/mistral-7b-ft-AgentInstruct")
+
+class MyStoppingCriteria(StoppingCriteria):
+  def __init__(self, target_sequence, prompt):
+      self.target_sequence = target_sequence
+      self.prompt=prompt
+
+  def __call__(self, input_ids, scores, **kwargs):
+      # Get the generated text as a string
+      generated_text = tokenizer.decode(input_ids[0])
+      generated_text = generated_text.replace(self.prompt,'')
+      # Check if the target sequence appears in the generated text
+      if self.target_sequence in generated_text:
+          return True  # Stop generation
+
+      return False  # Continue generation
+
+  def __len__(self):
+      return 1
+
+  def __iter__(self):
+      yield self
+
+def generate(
+        context,
+        max_new_tokens=256,
+        min_new_tokens=64,
+        temperature=0.3,
+        top_p=0.75,
+        top_k=40,
+        do_sample=False,
+        num_beams=2,
+        **kwargs,
+):
+    prompt = context
+    #print(prompt)
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].to("cuda")
+    attention_mask = inputs["attention_mask"].to("cuda")
+    generation_config = GenerationConfig(
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        do_sample=do_sample,
+        num_beams=num_beams,
+        **kwargs,
+    )
+    with torch.no_grad():
+        generation_output = model.generate(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            #generation_config=generation_config,
+            do_sample=True,
+            return_dict_in_generate=True,
+            output_scores=True,
+            max_new_tokens=max_new_tokens,
+            min_new_tokens=min_new_tokens,
+            early_stopping=False,
+            use_cache=True,
+            stopping_criteria=MyStoppingCriteria("### human:", prompt)
+        )
+    s = generation_output.sequences[0]
+    output = tokenizer.decode(s)
+    return output
+
+human = """### human: Among the reference ID of under 10 who got response by marketing department, compare their education status.
+There are 2 tables involved with this task. The name of the 1st table is Customers, and the headers of this table are ID,SEX,MARITAL_STATUS,GEOID,EDUCATIONNUM,OCCUPATION,age. The name of the 2nd table is Mailings1_2, and the headers of this table are REFID,REF_DATE,RESPONSE."""
+context = context + '\n' + human
+
+solution = generate(context)
+print(solution)
+```