nateraw/goliath-120b 🔢📝 → 📝

▶️ 237.5K runs 📅 Nov 2023 ⚙️ Cog 0.8.6
code-generation question-answering text-generation

About

An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one.

Example Output

Prompt:

"write me a blogpost all about parmigiano reggiano. Include helpful tips, like what to do with the rinds, whether you should buy pre-grated vs non-grated, etc, etc. Grumble about poor quality american Parmesan. "

Output

Title: The King of Cheeses: All Hail Parmigiano Reggiano!

Introduction:

Welcome, cheese aficionados! Today, we're going to dive into the world of the one and only Parmigiano Reggiano. That's right, I'm talking about the real deal, not that pre-grated, mass-produced "Parmesan" you find in American grocery stores. We're here to pay homage to the real thing - the King of Cheeses!

What is Parmigiano Reggiano?

Parmigiano Reggiano (pronounced par-mee-JYAH-no reh-JYAH-no) is a hard, aged Italian cheese that hails from the Emilia-Romagna region of Italy. It has been made using traditional methods for over 800 years! This PDO (Protected Designation of Origin) product means that it can only be called Parmigiano Reggiano if it's made within the specified area and adheres to strict production guidelines.

Why is it better than American "Parmesan"?

American "Parmesan" cheese is often a pale imitation of the real thing. It's typically made from a blend of cheeses, including Cheddar and other cheaper varieties, and is aged for a much shorter period - usually just a few months compared to the minimum 12-24 months for Parmigiano Reggiano. The result? A cheese that lacks depth of flavor, complexity, and that unmistakable umami kick.

Tips for Buying Parmigiano Reggiano:

  1. Look for the mark: Authentic Parmigiano Reggiano will have the words "Parmigiano Reggiano Stagionato" (or similar, depending on the aging) stamped on the rind. The rind should also have the brand of the dairy and the month and year of production.
  2. Check the texture: The cheese should be firm but slightly elastic. Avoid any pieces with cracks or mold (other than the natural mold that forms on the rind).
  3. Smell the cheese: It should have a nutty, grassy aroma with a hint of pungency. If it smells sour or ammonia-like, pass it by.

Grating your own vs. pre-grated:

While pre-grated Parmigiano Reggiano may seem convenient, nothing beats grating your own cheese. Pre-grated cheese can contain anti-caking agents and preservatives to maintain its consistency in the bag. Grating your own ensures you get the freshest, most flavorful cheese possible. Plus, it's therapeutic!

Using Parmigiano Reggiano Rinds:

Don't throw away those precious rinds! Here are some creative ways to use them:

  1. Soup and stew booster: Add the rind to your favorite soup or stew during cooking to infuse it with rich, cheesy flavor. Remove before serving.
  2. Risotto enhancer: Stir a piece of rind into your risotto during cooking for an extra burst of umami goodness.
  3. Pesto elevator: Throw a rind into your food processor when making pesto for a subtle cheesy undertone. Discard before serving.
  4. Mac and cheese upgrade: Add a rind to your mac and cheese sauce while it's simmering for a cheesier taste without adding more cheese.

Conclusion:

In conclusion, friends, there's no denying that Parmigiano Reggiano is in a league of its own. Next time you're at the cheese counter, skip the imposters and treat yourself to a wedge of the real deal. Your taste buds (and your pasta dishes) will thank you! And remember, always #SayNoToAmericanParmesan and #EatRealCheese.

Performance Metrics

82.37s Prediction Time
384.33s Total Time
All Input Parameters 
{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "write me a blogpost all about parmigiano reggiano. Include helpful tips, like what to do with the rinds, whether you should buy pre-grated vs non-grated, etc, etc. Grumble about poor quality american Parmesan. ",
  "temperature": 0.8,
  "max_new_tokens": 2048,
  "prompt_template": "You are a helpful AI assistant.\n\nUSER: {prompt}\nASSISTANT:",
  "presence_penalty": 1,
  "frequency_penalty": 0
}
Input Parameters
top_k Type: integerDefault: 50
The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 0.95
A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string
temperature Type: numberDefault: 0.8
The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 512
The maximum number of tokens the model should generate as output.
prompt_template Type: stringDefault: You are a helpful AI assistant. USER: {prompt} ASSISTANT:
The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder.
presence_penalty Type: numberDefault: 0
Presence penalty
frequency_penalty Type: numberDefault: 0
Frequency penalty
Output Schema

Output

Type: array • Items Type: string

Example Execution Logs 
INFO 11-16 06:28:37 async_llm_engine.py:370] Received request 0: prompt: 'You are a helpful AI assistant.\n\nUSER: write me a blogpost all about parmigiano reggiano. Include helpful tips, like what to do with the rinds, whether you should buy pre-grated vs non-grated, etc, etc. Grumble about poor quality american Parmesan. \nASSISTANT:', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=1.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.8, top_p=0.95, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=2048, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True), prompt token ids: None.
INFO 11-16 06:28:38 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.5%, CPU KV cache usage: 0.0%
INFO 11-16 06:28:43 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.9%, CPU KV cache usage: 0.0%
INFO 11-16 06:28:48 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 1.3%, CPU KV cache usage: 0.0%
INFO 11-16 06:28:53 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.5 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 1.6%, CPU KV cache usage: 0.0%
INFO 11-16 06:28:58 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.4 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 2.0%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:03 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.4 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 2.3%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:08 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.4 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 2.7%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:13 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.3 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 3.0%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:18 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.3 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 3.4%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:23 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 3.8%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:28 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 4.1%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:33 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 4.5%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:38 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 4.8%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:43 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 5.2%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:48 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 5.5%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:53 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 5.9%, CPU KV cache usage: 0.0%
INFO 11-16 06:29:58 llm_engine.py:624] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.2 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 6.2%, CPU KV cache usage: 0.0%
INFO 11-16 06:30:00 async_llm_engine.py:111] Finished request 0.
generation took 82.316s
Version Details
Version ID
39c0be5d2e96df975da94e8923535733d81179abed5f37c999afc5f7c33bf04e
Version Created
November 16, 2023
Run on Replicate →