Instructions to use kibrq/greedy-intersection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kibrq/greedy-intersection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kibrq/greedy-intersection", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("kibrq/greedy-intersection", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kibrq/greedy-intersection with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kibrq/greedy-intersection" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kibrq/greedy-intersection", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kibrq/greedy-intersection
- SGLang
How to use kibrq/greedy-intersection with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "kibrq/greedy-intersection" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kibrq/greedy-intersection", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "kibrq/greedy-intersection" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kibrq/greedy-intersection", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kibrq/greedy-intersection with Docker Model Runner:
docker model run hf.co/kibrq/greedy-intersection
Update model
Browse files- config.json +66 -2
- configuration_greedy.py +4 -4
config.json
CHANGED
|
@@ -8,8 +8,72 @@
|
|
| 8 |
},
|
| 9 |
"eos_token_id": 8,
|
| 10 |
"pad_token_id": 9,
|
| 11 |
-
"reciprocals":
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"torch_dtype": "float32",
|
| 14 |
"transformers_version": "4.21.1",
|
| 15 |
"vocab_size": 10
|
|
|
|
| 8 |
},
|
| 9 |
"eos_token_id": 8,
|
| 10 |
"pad_token_id": 9,
|
| 11 |
+
"reciprocals": [
|
| 12 |
+
[
|
| 13 |
+
4,
|
| 14 |
+
3
|
| 15 |
+
],
|
| 16 |
+
[
|
| 17 |
+
5,
|
| 18 |
+
2
|
| 19 |
+
],
|
| 20 |
+
[
|
| 21 |
+
6,
|
| 22 |
+
1
|
| 23 |
+
],
|
| 24 |
+
[
|
| 25 |
+
7,
|
| 26 |
+
0
|
| 27 |
+
]
|
| 28 |
+
],
|
| 29 |
+
"reducables": [
|
| 30 |
+
[
|
| 31 |
+
[
|
| 32 |
+
4
|
| 33 |
+
],
|
| 34 |
+
[
|
| 35 |
+
3
|
| 36 |
+
]
|
| 37 |
+
],
|
| 38 |
+
[
|
| 39 |
+
[
|
| 40 |
+
5
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
2
|
| 44 |
+
]
|
| 45 |
+
],
|
| 46 |
+
[
|
| 47 |
+
[
|
| 48 |
+
6
|
| 49 |
+
],
|
| 50 |
+
[
|
| 51 |
+
1
|
| 52 |
+
]
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
[
|
| 56 |
+
7
|
| 57 |
+
],
|
| 58 |
+
[
|
| 59 |
+
0
|
| 60 |
+
]
|
| 61 |
+
],
|
| 62 |
+
[
|
| 63 |
+
[
|
| 64 |
+
4,
|
| 65 |
+
5,
|
| 66 |
+
6,
|
| 67 |
+
7
|
| 68 |
+
],
|
| 69 |
+
[
|
| 70 |
+
0,
|
| 71 |
+
1,
|
| 72 |
+
2,
|
| 73 |
+
3
|
| 74 |
+
]
|
| 75 |
+
]
|
| 76 |
+
],
|
| 77 |
"torch_dtype": "float32",
|
| 78 |
"transformers_version": "4.21.1",
|
| 79 |
"vocab_size": 10
|
configuration_greedy.py
CHANGED
|
@@ -18,13 +18,13 @@ class GreedyConfig(PretrainedConfig):
|
|
| 18 |
|
| 19 |
freegroup_generators = list(range(1, freegroup_dimension + 1))
|
| 20 |
|
| 21 |
-
reciprocals = []
|
| 22 |
for x in freegroup_generators:
|
| 23 |
a, b = tokenizer.convert_tokens_to_ids([str(x), str(-x)])
|
| 24 |
-
reciprocals.append([a, b])
|
| 25 |
|
| 26 |
-
reducables = [[] for _ in range(freegroup_dimension + 1)]
|
| 27 |
-
for reducable, closure_generator in zip(reducables, [[x] for x in freegroup_generators] + [freegroup_generators[::]]):
|
| 28 |
reducable.append(tokenizer.convert_tokens_to_ids(list(map(str, closure_generator))))
|
| 29 |
reducable.append(tokenizer.convert_tokens_to_ids(list(map(str, tools.reciprocal(closure_generator)))))
|
| 30 |
|
|
|
|
| 18 |
|
| 19 |
freegroup_generators = list(range(1, freegroup_dimension + 1))
|
| 20 |
|
| 21 |
+
self.reciprocals = []
|
| 22 |
for x in freegroup_generators:
|
| 23 |
a, b = tokenizer.convert_tokens_to_ids([str(x), str(-x)])
|
| 24 |
+
self.reciprocals.append([a, b])
|
| 25 |
|
| 26 |
+
self.reducables = [[] for _ in range(freegroup_dimension + 1)]
|
| 27 |
+
for reducable, closure_generator in zip(self.reducables, [[x] for x in freegroup_generators] + [freegroup_generators[::]]):
|
| 28 |
reducable.append(tokenizer.convert_tokens_to_ids(list(map(str, closure_generator))))
|
| 29 |
reducable.append(tokenizer.convert_tokens_to_ids(list(map(str, tools.reciprocal(closure_generator)))))
|
| 30 |
|