Transformers
GGUF
English
mistral
Generated from Trainer
TheBloke commited on
Commit
17246e1
1 Parent(s): 2cd08be

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -6
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
  inference: false
7
  language:
8
  - en
9
- license: cc-by-nc-4.0
10
  model-index:
11
  - name: zephyr-7b-alpha
12
  results: []
@@ -316,7 +316,7 @@ Zephyr is a series of language models that are trained to act as helpful assista
316
 
317
  - **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
318
  - **Language(s) (NLP):** Primarily English
319
- - **License:** CC BY-NC 4.0
320
  - **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
321
 
322
  ### Model Sources
@@ -338,11 +338,23 @@ from transformers import pipeline
338
 
339
  pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-alpha", torch_dtype=torch.bfloat16, device_map="auto")
340
 
341
- # We use a variant of ChatML to format each message
342
- prompt_template = "<|system|>\n</s>\n<|user|>\n{query}</s>\n<|assistant|>\n"
343
- prompt = prompt_template.format(query="How many helicopters can a human eat in one sitting?")
 
 
 
 
 
 
344
  outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
345
- # Zero. Humans cannot consume or digest solid objects like helicopters, including their components such as rotor blades and engines. A human's diet is limited to food that they can swallow and break down through the process of digestion. Eating a helicopter would be physically impossible and could potentially cause serious harm if attempted.
 
 
 
 
 
 
346
  ```
347
 
348
  ## Bias, Risks, and Limitations
@@ -372,6 +384,7 @@ Zephyr 7B Alpha achieves the following results on the evaluation set:
372
  ### Training hyperparameters
373
 
374
  The following hyperparameters were used during training:
 
375
  - learning_rate: 5e-07
376
  - train_batch_size: 2
377
  - eval_batch_size: 4
 
6
  inference: false
7
  language:
8
  - en
9
+ license: mit
10
  model-index:
11
  - name: zephyr-7b-alpha
12
  results: []
 
316
 
317
  - **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
318
  - **Language(s) (NLP):** Primarily English
319
+ - **License:** MIT
320
  - **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
321
 
322
  ### Model Sources
 
338
 
339
  pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-alpha", torch_dtype=torch.bfloat16, device_map="auto")
340
 
341
+ # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
342
+ messages = [
343
+ {
344
+ "role": "system",
345
+ "content": "You are a friendly chatbot who always responds in the style of a pirate",
346
+ },
347
+ {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
348
+ ]
349
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
350
  outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
351
+ print(outputs[0]["generated_text"])
352
+ # <|system|>
353
+ # You are a friendly chatbot who always responds in the style of a pirate.</s>
354
+ # <|user|>
355
+ # How many helicopters can a human eat in one sitting?</s>
356
+ # <|assistant|>
357
+ # Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
358
  ```
359
 
360
  ## Bias, Risks, and Limitations
 
384
  ### Training hyperparameters
385
 
386
  The following hyperparameters were used during training:
387
+
388
  - learning_rate: 5e-07
389
  - train_batch_size: 2
390
  - eval_batch_size: 4