Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: update tests for new behavior

This commit is contained in:
drbh 2024-04-11 22:46:39 +00:00
parent ac74ec67c5
commit aa4f6a42b0
4 changed files with 17 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts.json
View File

@ -2,13 +2,19 @@
"choices": [
{
"finish_reason": "eos_token",
"index": 0,
"index": 1,
"logprobs": null,
"text": " PR for more information?"
},
{
"finish_reason": "length",
"index": 1,
"index": 3,
"logprobs": null,
"text": "hd20220811-"
},
{
"finish_reason": "length",
"index": 0,
"logprobs": null,
"text": "le Business Incubator is providing a workspace"
},
@ -16,29 +22,17 @@
"finish_reason": "length",
"index": 2,
"logprobs": null,
"text": "hd20220811-"
},
{
"finish_reason": "length",
"index": 3,
"logprobs": null,
"text": " severely flawed and often has a substandard"
},
{
"finish_reason": "length",
"index": 4,
"logprobs": null,
"text": "](https://i.imgur.com/as"
}
],
"created": 1712862968,
"created": 1712875413,
"id": "",
"model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"object": "text_completion",
"system_fingerprint": "1.4.5-native",
"usage": {
"completion_tokens": 46,
"prompt_tokens": 10,
"total_tokens": 56
"completion_tokens": 36,
"prompt_tokens": 8,
"total_tokens": 44
}
}

2
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts_stream.json
View File

@ -1 +1 @@
"<ClientResponse(http://localhost:9483/v1/completions) [200 OK]>\n<CIMultiDictProxy('Content-Type': 'text/event-stream', 'Cache-Control': 'no-cache', 'x-compute-type': '1-nvidia-a10g', 'x-compute-characters': '72', 'x-accel-buffering': 'no', 'Access-Control-Allow-Origin': '*', 'Vary': 'origin', 'Vary': 'access-control-request-method', 'Vary': 'access-control-request-headers', 'Transfer-Encoding': 'chunked', 'Date': 'Thu, 11 Apr 2024 19:19:32 GMT')>\n"
"<ClientResponse(http://localhost:8041/v1/completions) [200 OK]>\n<CIMultiDictProxy('Content-Type': 'text/event-stream', 'Cache-Control': 'no-cache', 'x-compute-type': '1-nvidia-a10g', 'x-compute-characters': '72', 'x-accel-buffering': 'no', 'Access-Control-Allow-Origin': '*', 'Vary': 'origin', 'Vary': 'access-control-request-method', 'Vary': 'access-control-request-headers', 'Transfer-Encoding': 'chunked', 'Date': 'Thu, 11 Apr 2024 22:43:33 GMT')>\n"

2
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_single_prompt.json
View File

@ -7,7 +7,7 @@
"text": " PR for flake8"
}
],
"created": 1712862926,
"created": 1712875413,
"id": "",
"model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"object": "text_completion",

6
integration-tests/models/test_completion_prompts.py
View File

@ -47,7 +47,7 @@ def test_flash_llama_completion_many_prompts(flash_llama_completion, response_sn
f"{flash_llama_completion.base_url}/v1/completions",
json={
"model": "tgi",
"prompt": ["Say", "this", "is", "a", "test"],
"prompt": ["Say", "this", "is", "a"],
"max_tokens": 10,
"seed": 0,
},
@ -55,11 +55,11 @@ def test_flash_llama_completion_many_prompts(flash_llama_completion, response_sn
stream=False,
)
response = response.json()
assert len(response["choices"]) == 5
assert len(response["choices"]) == 4
all_indexes = [choice["index"] for choice in response["choices"]]
all_indexes.sort()
assert all_indexes == [0, 1, 2, 3, 4]
assert all_indexes == [0, 1, 2, 3]
response == response_snapshot