huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove duplicate test

Browse Source
This commit is contained in:
drbh 2024-02-29 23:18:22 +00:00
parent 06fd5affa0
commit 1eff07c0e4
2 changed files with 0 additions and 339 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

274
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_non_flash_llama_grammar_json.json
View File

@ -1,274 +0,0 @@
{
"details": {
"best_of_sequences": null,
"finish_reason": "eos_token",
"generated_tokens": 30,
"prefill": [
{
"id": 1,
"logprob": null,
"text": "<s>"
},
{
"id": 5235,
"logprob": -10.061389,
"text": "info"
},
{
"id": 29901,
"logprob": -3.2349052,
"text": ":"
},
{
"id": 13260,
"logprob": -10.626516,
"text": "dav"
},
{
"id": 333,
"logprob": -0.08372568,
"text": "id"
},
{
"id": 8753,
"logprob": -7.5279083,
"text": "hol"
},
{
"id": 17559,
"logprob": -3.8427715,
"text": "tz"
},
{
"id": 763,
"logprob": -10.143592,
"text": "like"
},
{
"id": 10697,
"logprob": -10.200588,
"text": "trees"
},
{
"id": 322,
"logprob": -2.5744739,
"text": "and"
},
{
"id": 756,
"logprob": -7.4822097,
"text": "has"
},
{
"id": 1023,
"logprob": -5.043413,
"text": "two"
},
{
"id": 274,
"logprob": -5.326814,
"text": "c"
},
{
"id": 1446,
"logprob": -0.67299384,
"text": "ats"
},
{
"id": 29889,
"logprob": -0.999048,
"text": "."
},
{
"id": 29871,
"logprob": -4.2404404,
"text": ""
}
],
"seed": null,
"tokens": [
{
"id": 6377,
"logprob": -0.1497998,
"special": false,
"text": "{\""
},
{
"id": 29888,
"logprob": -0.1359236,
"special": false,
"text": "f"
},
{
"id": 12935,
"logprob": -0.01771052,
"special": false,
"text": "irs"
},
{
"id": 29873,
"logprob": -0.00084543246,
"special": false,
"text": "t"
},
{
"id": 1170,
"logprob": -0.0053624124,
"special": false,
"text": "Name"
},
{
"id": 4710,
"logprob": -0.13352497,
"special": false,
"text": "\":\""
},
{
"id": 19504,
"logprob": -0.8816582,
"special": false,
"text": "David"
},
{
"id": 3284,
"logprob": -0.1636697,
"special": false,
"text": "\",\""
},
{
"id": 29882,
"logprob": -0.08828322,
"special": false,
"text": "h"
},
{
"id": 711,
"logprob": -0.66238964,
"special": false,
"text": "ob"
},
{
"id": 1609,
"logprob": -5.566919e-05,
"special": false,
"text": "by"
},
{
"id": 4710,
"logprob": -0.2296004,
"special": false,
"text": "\":\""
},
{
"id": 29911,
"logprob": -2.3745353,
"special": false,
"text": "T"
},
{
"id": 11003,
"logprob": -0.032119535,
"special": false,
"text": "rees"
},
{
"id": 3284,
"logprob": -0.22055298,
"special": false,
"text": "\",\""
},
{
"id": 4230,
"logprob": -0.067228675,
"special": false,
"text": "last"
},
{
"id": 1170,
"logprob": -0.0035023084,
"special": false,
"text": "Name"
},
{
"id": 4710,
"logprob": -0.004494921,
"special": false,
"text": "\":\""
},
{
"id": 29950,
"logprob": -0.12524654,
"special": false,
"text": "H"
},
{
"id": 14339,
"logprob": -0.009601957,
"special": false,
"text": "olt"
},
{
"id": 29920,
"logprob": -0.00041619223,
"special": false,
"text": "z"
},
{
"id": 3284,
"logprob": -0.116980776,
"special": false,
"text": "\",\""
},
{
"id": 29876,
"logprob": -0.2994127,
"special": false,
"text": "n"
},
{
"id": 398,
"logprob": -0.0030563807,
"special": false,
"text": "um"
},
{
"id": 29907,
"logprob": -0.37736154,
"special": false,
"text": "C"
},
{
"id": 1446,
"logprob": -0.00031073033,
"special": false,
"text": "ats"
},
{
"id": 1115,
"logprob": -0.0021851014,
"special": false,
"text": "\":"
},
{
"id": 29906,
"logprob": -0.07180126,
"special": false,
"text": "2"
},
{
"id": 29913,
"logprob": -0.018707855,
"special": false,
"text": "}"
},
{
"id": 2,
"logprob": 0.0,
"special": true,
"text": "</s>"
}
],
"top_tokens": null
},
"generated_text": "{\"firstName\":\"David\",\"hobby\":\"Trees\",\"lastName\":\"Holtz\",\"numCats\":2}"
}

65
integration-tests/models/test_flash_grammar_llama.py
View File

@ -144,68 +144,3 @@ async def test_flash_llama_grammar_single_load_instance(
assert response.generated_text == "123456@gmail.com"
assert response == response_snapshot
@pytest.fixture(scope="module")
def non_flash_llama_grammar_handle(launcher):
with launcher(
"TinyLlama/TinyLlama-1.1B-Chat-v1.0",
num_shard=1,
disable_grammar_support=False,
use_flash_attention=False,
) as handle:
yield handle
@pytest.fixture(scope="module")
async def non_flash_llama_grammar(non_flash_llama_grammar_handle):
await non_flash_llama_grammar_handle.health(300)
return non_flash_llama_grammar_handle.client
@pytest.mark.asyncio
async def test_non_flash_llama_grammar_json(non_flash_llama_grammar, response_snapshot):
response = await non_flash_llama_grammar.generate(
"info: david holtz like trees and has two cats. ",
max_new_tokens=100,
decoder_input_details=True,
seed=0,
grammar={
"type": GrammarType.Json,
"value": json.dumps(
{
"type": "object",
"$id": "https://example.com/person.schema.json",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Person",
"properties": {
"firstName": {
"type": "string",
"description": "The person'''s first name.",
},
"lastName": {
"type": "string",
"description": "The person'''s last name.",
},
"hobby": {
"description": "The person'''s hobby.",
"type": "string",
},
"numCats": {
"description": "The number of cats the person has.",
"type": "integer",
"minimum": 0,
},
},
"required": ["firstName", "lastName", "hobby", "numCats"],
}
),
},
)
assert response.details.generated_tokens == 30
assert (
response.generated_text
== '{"firstName":"David","hobby":"Trees","lastName":"Holtz","numCats":2}'
)
assert response == response_snapshot