baseten
/

whisper_trt_medium_NVIDIA_A100_SXM4_80GB_0_12_0_dev2024071600

Model card Files Files and versions Community

bolasim commited on Aug 23

Commit

4a9a3d9

•

1 Parent(s): 4803239

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

.gitattributes +2 -0
decoder/config.json +162 -0
decoder/rank0.engine +3 -0
encoder/config.json +140 -0
encoder/rank0.engine +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+decoder/rank0.engine filter=lfs diff=lfs merge=lfs -text
+encoder/rank0.engine filter=lfs diff=lfs merge=lfs -text

decoder/config.json ADDED Viewed

	@@ -0,0 +1,162 @@

+{
+    "version": "0.12.0.dev2024071600",
+    "pretrained_config": {
+        "architecture": "DecoderModel",
+        "dtype": "float16",
+        "vocab_size": 51865,
+        "hidden_size": 1024,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "logits_dtype": "float16",
+        "norm_epsilon": 1e-05,
+        "position_embedding_type": "learned_absolute",
+        "max_position_embeddings": 448,
+        "num_key_value_heads": 16,
+        "intermediate_size": 4096,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_ep_size": 1
+        },
+        "quantization": {
+            "quant_algo": null,
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": null,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "share_embedding_table": false,
+        "head_size": 64,
+        "qk_layernorm": false,
+        "use_prompt_tuning": false,
+        "has_position_embedding": true,
+        "layernorm_type": 0,
+        "has_attention_qkvo_bias": true,
+        "has_mlp_bias": true,
+        "has_model_final_layernorm": true,
+        "has_embedding_layernorm": false,
+        "has_embedding_scale": false,
+        "ffn_hidden_size": 4096,
+        "q_scaling": 1.0,
+        "layernorm_position": 0,
+        "relative_attention": false,
+        "max_distance": 0,
+        "num_buckets": 0,
+        "model_type": "whisper",
+        "rescale_before_lm_head": false,
+        "encoder_hidden_size": 1024,
+        "encoder_num_heads": 16,
+        "encoder_head_size": null,
+        "skip_cross_qkv": false,
+        "type_vocab_size": null,
+        "encoder_num_kv_heads": null,
+        "mlp_type": 0,
+        "residual_scaling": 1.0,
+        "has_lm_head_bias": false
+    },
+    "build_config": {
+        "max_input_len": 256,
+        "max_seq_len": 1000,
+        "opt_batch_size": null,
+        "max_batch_size": 8,
+        "max_beam_width": 5,
+        "max_num_tokens": 8000,
+        "opt_num_tokens": null,
+        "max_prompt_embedding_table_size": 0,
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "builder_opt": null,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {}
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": "A100-SXM-80GB",
+            "cluster_info": null,
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {
+                "past_key_value_(\\d+)": "present_key_value_\\1"
+            },
+            "same_spec_io": {},
+            "sharded_io_allowlist": [
+                "past_key_value_\\d+",
+                "present_key_value_\\d*"
+            ],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "float16",
+            "bert_attention_plugin": "float16",
+            "gpt_attention_plugin": "float16",
+            "gemm_plugin": "float16",
+            "gemm_swiglu_plugin": null,
+            "smooth_quant_gemm_plugin": null,
+            "identity_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "nccl_plugin": null,
+            "lookup_plugin": null,
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": null,
+            "mamba_conv1d_plugin": "auto",
+            "context_fmha": true,
+            "context_fmha_fp32_acc": false,
+            "paged_kv_cache": false,
+            "remove_input_padding": false,
+            "use_custom_all_reduce": false,
+            "reduce_fusion": false,
+            "multi_block_mode": false,
+            "enable_xqa": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": true,
+            "streamingllm": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1500,
+        "use_fused_mlp": false
+    }
+}

decoder/rank0.engine ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce510bcdee23609787e492a7bfd6162aa5ba4e04acee2ce552e0d1837d8b605f
+size 1028387332

encoder/config.json ADDED Viewed

	@@ -0,0 +1,140 @@

+{
+    "version": "0.12.0.dev2024071600",
+    "pretrained_config": {
+        "architecture": "WhisperEncoder",
+        "dtype": "float16",
+        "vocab_size": 51865,
+        "hidden_size": 1024,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "logits_dtype": "float32",
+        "norm_epsilon": 1e-05,
+        "position_embedding_type": "learned_absolute",
+        "max_position_embeddings": null,
+        "num_key_value_heads": 16,
+        "intermediate_size": 4096,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_ep_size": 1
+        },
+        "quantization": {
+            "quant_algo": null,
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": null,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "share_embedding_table": false,
+        "head_size": 64,
+        "qk_layernorm": false,
+        "n_mels": 80,
+        "n_audio_ctx": 1500,
+        "num_languages": 99
+    },
+    "build_config": {
+        "max_input_len": 1500,
+        "max_seq_len": 2048,
+        "opt_batch_size": null,
+        "max_batch_size": 8,
+        "max_beam_width": 1,
+        "max_num_tokens": 16384,
+        "opt_num_tokens": null,
+        "max_prompt_embedding_table_size": 0,
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "builder_opt": null,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {}
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": "A100-SXM-80GB",
+            "cluster_info": null,
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {
+                "past_key_value_(\\d+)": "present_key_value_\\1"
+            },
+            "same_spec_io": {},
+            "sharded_io_allowlist": [
+                "past_key_value_\\d+",
+                "present_key_value_\\d*"
+            ],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "float16",
+            "bert_attention_plugin": "float16",
+            "gpt_attention_plugin": "auto",
+            "gemm_plugin": null,
+            "gemm_swiglu_plugin": null,
+            "smooth_quant_gemm_plugin": null,
+            "identity_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "nccl_plugin": null,
+            "lookup_plugin": null,
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": null,
+            "mamba_conv1d_plugin": "auto",
+            "context_fmha": true,
+            "context_fmha_fp32_acc": false,
+            "paged_kv_cache": false,
+            "remove_input_padding": false,
+            "use_custom_all_reduce": false,
+            "reduce_fusion": false,
+            "multi_block_mode": false,
+            "enable_xqa": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": true,
+            "streamingllm": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1024,
+        "use_fused_mlp": false
+    }
+}

encoder/rank0.engine ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:49399106e1b8860bd629a071c50a25b844f000a88e84fa0f3e2c45e2aac3eaac
+size 620959244