Update README.md

README.md

@@ -2,6 +2,9 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+- HC3
+- chatGPT
+- assistant
 datasets:
 - pszemraj/HC3-textgen-qa
 metrics:
@@ -9,11 +12,12 @@ metrics:
 inference: False
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # pythia-6.9b-deduped for general QA
 
+<a href="https://colab.research.google.com/gist/pszemraj/351f04fc2afb6346c763885f127284ef/pythia-6-9b-deduped-for-general-qa.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
 This model is a fine-tuned version of [EleutherAI/pythia-6.9b-deduped](https://huggingface.co/EleutherAI/pythia-6.9b-deduped) on the pszemraj/HC3-textgen-qa dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2372
@@ -42,16 +46,17 @@ tokenizer = AutoTokenizer.from_pretrained("pszemraj/pythia-6.9b-HC3")
 
 model = AutoModelForCausalLM.from_pretrained(
     "pszemraj/pythia-6.9b-HC3", load_in_8bit=True, device_map="auto"
-) # shards are ~4GB each
+) # shards are ~4GB each, there are eight total
 
 prompt = "I was wondering how much wood a woodchuck could chuck? <answer>"
 inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=300) # default generation config (+ 300 tokens)
-result = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+result = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+result = result.split("<end_answer>")[0].strip()
 
 import pprint as pp
 
-pp.pprint(result[0])
+pp.pprint(result)
 ```
 
 The defautl `GenerationConfig` uses contrastive search with `top_k=4` and `penalty_alpha=0.6`. For more information on inference and parameters to use, see [the transformers docs](https://huggingface.co/docs/transformers/generation_strategies#decoding-strategies).
@@ -59,7 +64,7 @@ The defautl `GenerationConfig` uses contrastive search with `top_k=4` and `penal
 ## Intended uses & limitations
 
 - **Intended use:** research/exploration into comparing RLHF tuning vs. "guided"/specific tuning on "quality" datasets/responses of _"what the human would want as answer anyway"_
-- This is not trained/fine-tuned with RLHF and therefore will not be as helpful/generalizable/safe as chatGPT.
+- This is **not** trained/fine-tuned with RLHF and therefore will not be as helpful/generalizable/safe as chatGPT.
 
 ## Training and evaluation data
 
@@ -81,6 +86,8 @@ model-index:
 
 ## Training procedure
 
+Two epochs on the `pszemraj/HC3-textgen-qa` dataset.
+
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |