mwitiderrick commited on
Commit
f9d041b
1 Parent(s): a82f2ba

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: LLM360/AmberChat
3
+ inference: false
4
+ model_type: llama
5
+ prompt_template: |
6
+ ### Assistant:\n
7
+ ### Human:{prompt}
8
+ ### Assistant:
9
+ quantized_by: mwitiderrick
10
+ tags:
11
+ - deepsparse
12
+ ---
13
+ # AmberChat - DeepSparse
14
+ This repo contains model files for [AmberChat](https://huggingface.co/LLM360/AmberChat) optimized for [DeepSparse](https://github.com/neuralmagic/deepsparse), a CPU inference runtime for sparse models.
15
+
16
+ This model was quantized and pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [SparseML](https://github.com/neuralmagic/sparseml).
17
+ ## Inference
18
+ Install [DeepSparse LLM](https://github.com/neuralmagic/deepsparse) for fast inference on CPUs:
19
+ ```bash
20
+ pip install deepsparse-nightly[llm]
21
+ ```
22
+ Run in a [Python pipeline](https://github.com/neuralmagic/deepsparse/blob/main/docs/llms/text-generation-pipeline.md):
23
+ ```python
24
+ from deepsparse import TextGeneration
25
+
26
+ template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"
27
+
28
+ prompt = "How to make banana bread?"
29
+
30
+ input_str = template.format(prompt=prompt)
31
+
32
+ model = TextGeneration(model_path="hf:nm-testing/AmberChat-pruned50-quant")
33
+
34
+ print(model(input_str, max_new_tokens=200).generations[0].text)
35
+ """
36
+
37
+ """
38
+ ```
39
+ ## Example 2
40
+ ```
41
+ from deepsparse import TextGeneration
42
+ generation_config = {
43
+ "repetition_penalty": 2.0,
44
+ "do_sample": True,
45
+ "max_new_tokens": 500,
46
+ }
47
+ template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"
48
+
49
+ prompt = "How to make banana bread?"
50
+
51
+ input_str = template.format(prompt=prompt)
52
+
53
+ model = TextGeneration(model_path="deployment")
54
+
55
+ print(model(input_str, generation_config=generation_config).generations[0].text)
56
+ """
57
+
58
+ """
59
+
60
+ ```
61
+ ## Prompt template
62
+ ```
63
+
64
+ ### Assistant:
65
+ ### Human:{prompt}
66
+ ### Assistant:
67
+ ```
68
+ ## Sparsification
69
+ For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.
70
+
71
+ ```bash
72
+ git clone https://github.com/neuralmagic/sparseml
73
+ pip install -e "sparseml[transformers]"
74
+ python sparseml/src/sparseml/transformers/sparsification/obcq/obcq.py LLM360/AmberChat open_platypus --recipe recipe.yaml --save True
75
+ python sparseml/src/sparseml/transformers/sparsification/obcq/export.py --task text-generation --model_path obcq_deployment
76
+ cp deployment/model.onnx deployment/model-orig.onnx
77
+ ```
78
+ Run this kv-cache injection to speed up the model at inference by caching the Key and Value states:
79
+ ```python
80
+ import os
81
+ import onnx
82
+ from sparseml.exporters.kv_cache_injector import KeyValueCacheInjector
83
+ input_file = "deployment/model-orig.onnx"
84
+ output_file = "deployment/model.onnx"
85
+ model = onnx.load(input_file, load_external_data=False)
86
+ model = KeyValueCacheInjector(model_path=os.path.dirname(input_file)).apply(model)
87
+ onnx.save(model, output_file)
88
+ print(f"Modified model saved to: {output_file}")
89
+ ```
90
+ Follow the instructions on our [One Shot With SparseML](https://github.com/neuralmagic/sparseml/tree/main/src/sparseml/transformers/sparsification/obcq) page for a step-by-step guide for performing one-shot quantization of large language models.
91
+ ## Slack
92
+
93
+ For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)