huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update llama gptq.

Browse Source
This commit is contained in:
Nicolas Patry 2024-02-08 15:42:33 +00:00
parent bc157af9b0
commit a76821e0b2
3 changed files with 188 additions and 182 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq.json
View File

@ -11,78 +11,79 @@
},
{
"id": 4321,
"logprob": -9.59375,
"logprob": -9.7890625,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.6640625,
"logprob": -9.625,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 29918,
"logprob": -2.3867188,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -2.8183594,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -1.6367188,
"logprob": -2.3359375,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -1.0527344,
"logprob": -1.8779297,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.6542969,
"logprob": -1.2744141,
"special": false,
"text": " request"
},
{
"id": 29918,
"logprob": -0.056121826,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -0.01600647,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -0.87939453,
"logprob": -1.6933594,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.7529297,
"logprob": -1.4648438,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.2980957,
"logprob": -0.15600586,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.8027344,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.23022461,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.0069885254,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.02218628,
"special": false,
"text": "\n"
}
]
],
"top_tokens": null
},
"generated_text": "_uri\nTest request_uri\nTest request"
"generated_text": "\nTest request\nTest request\nTest request\n"
}

25
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq_all_params.json
View File

@ -11,12 +11,12 @@
},
{
"id": 4321,
"logprob": -9.6015625,
"logprob": -9.84375,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.6640625,
"logprob": -9.6015625,
"text": "request"
}
],
@ -24,13 +24,13 @@
"tokens": [
{
"id": 29899,
"logprob": -1.1640625,
"logprob": -1.5625,
"special": false,
"text": "-"
},
{
"id": 1454,
"logprob": -0.07543945,
"logprob": -0.20410156,
"special": false,
"text": "for"
},
@ -54,19 +54,19 @@
},
{
"id": 396,
"logprob": -0.2956543,
"logprob": -0.27685547,
"special": false,
"text": " #"
},
{
"id": 29906,
"logprob": -0.52734375,
"logprob": -0.4970703,
"special": false,
"text": "2"
},
{
"id": 29900,
"logprob": -0.6899414,
"logprob": -0.80615234,
"special": false,
"text": "0"
},
@ -77,12 +77,13 @@
"text": "1"
},
{
"id": 29946,
"logprob": -1.5068359,
"id": 29955,
"logprob": -1.0751953,
"special": false,
"text": "4"
"text": "7"
}
]
],
"top_tokens": null
},
"generated_text": "Test request-for-comment: #2014"
"generated_text": "Test request-for-comment: #2017"
}

276
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq_load.json
View File

@ -12,80 +12,81 @@
},
{
"id": 4321,
"logprob": -9.6015625,
"logprob": -9.828125,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.671875,
"logprob": -9.609375,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 29918,
"logprob": -2.3828125,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -2.8105469,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -1.6396484,
"logprob": -2.3300781,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -1.0546875,
"logprob": -1.8740234,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.6513672,
"logprob": -1.2646484,
"special": false,
"text": " request"
},
{
"id": 29918,
"logprob": -0.056365967,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -0.016082764,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -0.87841797,
"logprob": -1.7158203,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.7548828,
"logprob": -1.4667969,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.29711914,
"logprob": -0.15344238,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.81591797,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.22973633,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.007045746,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.021957397,
"special": false,
"text": "\n"
}
]
],
"top_tokens": null
},
"generated_text": "_uri\nTest request_uri\nTest request"
"generated_text": "\nTest request\nTest request\nTest request\n"
},
{
"details": {
@ -100,80 +101,81 @@
},
{
"id": 4321,
"logprob": -9.6015625,
"logprob": -9.84375,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.6640625,
"logprob": -9.59375,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 29918,
"logprob": -2.3828125,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -2.828125,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -1.6386719,
"logprob": -2.3378906,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -1.0527344,
"logprob": -1.8779297,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.6542969,
"logprob": -1.2636719,
"special": false,
"text": " request"
},
{
"id": 29918,
"logprob": -0.055877686,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -0.016021729,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -0.8769531,
"logprob": -1.6992188,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.7583008,
"logprob": -1.4589844,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.29833984,
"logprob": -0.15344238,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.79052734,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.22937012,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.007041931,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.022140503,
"special": false,
"text": "\n"
}
]
],
"top_tokens": null
},
"generated_text": "_uri\nTest request_uri\nTest request"
"generated_text": "\nTest request\nTest request\nTest request\n"
},
{
"details": {
@ -188,80 +190,81 @@
},
{
"id": 4321,
"logprob": -9.6015625,
"logprob": -9.84375,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.671875,
"logprob": -9.609375,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 29918,
"logprob": -2.3847656,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -2.8144531,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -1.6396484,
"logprob": -2.3261719,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -1.0527344,
"logprob": -1.8730469,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.65478516,
"logprob": -1.2587891,
"special": false,
"text": " request"
},
{
"id": 29918,
"logprob": -0.056243896,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -0.016143799,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -0.8808594,
"logprob": -1.6894531,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.75341797,
"logprob": -1.46875,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.2956543,
"logprob": -0.1541748,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.80322266,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.22912598,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.0070495605,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.021606445,
"special": false,
"text": "\n"
}
]
],
"top_tokens": null
},
"generated_text": "_uri\nTest request_uri\nTest request"
"generated_text": "\nTest request\nTest request\nTest request\n"
},
{
"details": {
@ -276,79 +279,80 @@
},
{
"id": 4321,
"logprob": -9.6015625,
"logprob": -9.84375,
"text": "Test"
},
{
"id": 2009,
"logprob": -9.6640625,
"logprob": -9.6015625,
"text": "request"
}
],
"seed": null,
"tokens": [
{
"id": 29918,
"logprob": -2.3769531,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -2.8183594,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -1.6396484,
"logprob": -2.3320312,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -1.0546875,
"logprob": -1.875,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.65478516,
"logprob": -1.2646484,
"special": false,
"text": " request"
},
{
"id": 29918,
"logprob": -0.05557251,
"special": false,
"text": "_"
},
{
"id": 5338,
"logprob": -0.01612854,
"special": false,
"text": "uri"
},
{
"id": 13,
"logprob": -0.8730469,
"logprob": -1.6884766,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.7519531,
"logprob": -1.4589844,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.29785156,
"logprob": -0.15185547,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.79833984,
"special": false,
"text": "\n"
},
{
"id": 3057,
"logprob": -0.22827148,
"special": false,
"text": "Test"
},
{
"id": 2009,
"logprob": -0.006996155,
"special": false,
"text": " request"
},
{
"id": 13,
"logprob": -0.021560669,
"special": false,
"text": "\n"
}
]
],
"top_tokens": null
},
"generated_text": "_uri\nTest request_uri\nTest request"
"generated_text": "\nTest request\nTest request\nTest request\n"
}
]