facebook/xglm-7.5B

`facebook/xglm-7.5B` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-generation` task in the `transformers` library. If you want to learn m…

azureFoundry/HuggingFace/facebook-xglm-7.5b@3

facebook/xglm-7.5B is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the text-generation task in the transformers library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, you can find this information on the model's dedicated Model Card on the Hugging Face Hub.

Specifications & capabilities

Input
text
Output
text
Published model ID
xglm-7.5B

Evaluations

1–20 / 2,657

LLM-Perf

1,037.222

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.759616
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.21.4
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
4909897803340eb7e6b6fac3fe3ecefffcf283b481da328f3cd4a1646a3773da
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

1,037.222

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-bnb-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.759616
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.21.4
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-bnb-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
c2cea1bf659b09f3af0a9282c4436002f77fd79191c0227f7139dd49c9fe071d
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

1,031.361

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

1,031.361

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

1,030.779

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
0c30c8771a345d5292e04c5586e2d1e48770c6005797652b7c22666e75a1b772
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

1,030.779

source id
llmPerf
leaderboard name
load memory max_ram
dimension
runtime
metric
load memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
5a9b375f6f28091ca8e42adee42f402e3251b53a0e08f4ad5d4a44be30b7601b
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p95
dimension
runtime
metric
load latency p95
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p95
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency mean
dimension
runtime
metric
load latency mean
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency mean
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p99
dimension
runtime
metric
load latency p99
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p99
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p50
dimension
runtime
metric
load latency p50
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p50
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p99
dimension
runtime
metric
load latency p99
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p99
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p90
dimension
runtime
metric
load latency p90
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p90
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p50
dimension
runtime
metric
load latency p50
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p50
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency mean
dimension
runtime
metric
load latency mean
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency mean
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p95
dimension
runtime
metric
load latency p95
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p95
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
44e26e0e31a5059c441e0ef887206687f9d8e10dc1c7aa3cec7b668d8f91eea9
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

6.982

source id
llmPerf
leaderboard name
load latency p90
dimension
runtime
metric
load latency p90
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.261056
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.12.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.44.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.4.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load latency p90
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-unquantized-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
a6c8c18da67c77f09274c2af41ecd839525d3180eec11b6337ee1cdb883283fc
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

0

source id
llmPerf
leaderboard name
load energy gpu
dimension
runtime
metric
load energy gpu
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cpu
config.backend.library
transformers
config.backend.version
2.4.1+cpu
config.environment.cpu
Intel(R) Xeon(R) Platinum 8488C
config.backend.eval_mode
True
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
32
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66326.188032
config.backend.autocast_enabled
False
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.environment.transformers_version
4.45.1
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.5.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
load energy gpu
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
e788b9b9d4d082470b2df460cdad66d1cf25fe9a372f73cf3e52ea54f150acd3
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

0

source id
llmPerf
leaderboard name
decode memory max_process_vram
dimension
runtime
metric
decode memory max_process_vram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-gptq-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.759616
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.13.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
gptq
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.backend.quantization_config.bits
4
config.environment.transformers_version
4.45.1
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.backend.quantization_config.version
2
config.environment.optimum_benchmark_version
0.5.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.model_seqlen
256
config.backend.quantization_config.use_exllama
True
metric_kind
decode memory max_process_vram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-gptq-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
7f68e3cf9e89fdf942900cbcd212275a5a2c92250486eab35fc36875d4adfa2a
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

0

source id
llmPerf
leaderboard name
prefill memory max_process_vram
dimension
runtime
metric
prefill memory max_process_vram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.3.0+cu121
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.29792
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.10.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.19.2
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.30.1
config.environment.transformers_version
4.40.2
config.scenario.input_shapes.batch_size
1
config.backend.hub_kwargs.force_download
False
config.scenario.input_shapes.num_choices
2
config.backend.hub_kwargs.local_files_only
False
config.backend.hub_kwargs.trust_remote_code
True
config.environment.optimum_benchmark_version
0.2.0
config.scenario.input_shapes.sequence_length
256
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill memory max_process_vram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
model_revision
main
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
27
benchmark_evaluation
true
comparison_configuration_sha256
fcfb76da9f87d97711043c800a48ac332809b752f60719639f61446198d5349f
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

LLM-Perf

0

source id
llmPerf
leaderboard name
load memory max_process_vram
dimension
runtime
metric
load memory max_process_vram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-gptq-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.4.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
xglm
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.759616
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.13.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
gptq
config.environment.optimum_version
1.22.0
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
0.34.2
config.backend.quantization_config.bits
4
config.environment.transformers_version
4.45.1
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.backend.quantization_config.version
2
config.environment.optimum_benchmark_version
0.5.0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.model_seqlen
256
config.backend.quantization_config.use_exllama
True
metric_kind
load memory max_process_vram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-gptq-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
3
benchmark_evaluation
true
comparison_configuration_sha256
7f68e3cf9e89fdf942900cbcd212275a5a2c92250486eab35fc36875d4adfa2a
complete_configuration_location
source record config and original CSV artifact
source model id
facebook/xglm-7.5B
Original result ↗

Provider specifications & access

1–1 / 1

facebook/xglm-7.5B ↗

source model id
HuggingFace/facebook-xglm-7.5b@3
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
mit
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    31 / 100

    source id
    stanfordFMTI
    canonical model id
    azureFoundry/HuggingFace/facebook-xglm-7.5b@3
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Meta
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    31 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–8 / 8

    Hugging Face · Model repository ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–5 / 5

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace