baseten
/

deepseek-v3-engine-32k

Model card Files Files and versions Community

aspctu commited on 9 days ago

Commit

6d92381

verified ·

1 Parent(s): b5b8eca

Upload folder using huggingface_hub

Browse files

Files changed (18) hide show

.gitattributes +16 -0
config.json +191 -0
rank0.engine +3 -0
rank1.engine +3 -0
rank10.engine +3 -0
rank11.engine +3 -0
rank12.engine +3 -0
rank13.engine +3 -0
rank14.engine +3 -0
rank15.engine +3 -0
rank2.engine +3 -0
rank3.engine +3 -0
rank4.engine +3 -0
rank5.engine +3 -0
rank6.engine +3 -0
rank7.engine +3 -0
rank8.engine +3 -0
rank9.engine +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,19 @@ 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
+rank0.engine filter=lfs diff=lfs merge=lfs -text
+rank1.engine filter=lfs diff=lfs merge=lfs -text
+rank10.engine filter=lfs diff=lfs merge=lfs -text
+rank11.engine filter=lfs diff=lfs merge=lfs -text
+rank12.engine filter=lfs diff=lfs merge=lfs -text
+rank13.engine filter=lfs diff=lfs merge=lfs -text
+rank14.engine filter=lfs diff=lfs merge=lfs -text
+rank15.engine filter=lfs diff=lfs merge=lfs -text
+rank2.engine filter=lfs diff=lfs merge=lfs -text
+rank3.engine filter=lfs diff=lfs merge=lfs -text
+rank4.engine filter=lfs diff=lfs merge=lfs -text
+rank5.engine filter=lfs diff=lfs merge=lfs -text
+rank6.engine filter=lfs diff=lfs merge=lfs -text
+rank7.engine filter=lfs diff=lfs merge=lfs -text
+rank8.engine filter=lfs diff=lfs merge=lfs -text
+rank9.engine filter=lfs diff=lfs merge=lfs -text

config.json ADDED Viewed

	@@ -0,0 +1,191 @@

+{
+    "version": "0.17.0.dev2024121700",
+    "pretrained_config": {
+        "mlp_bias": false,
+        "attn_bias": false,
+        "rotary_base": 10000,
+        "rotary_scaling": {
+            "beta_fast": 32,
+            "beta_slow": 1,
+            "factor": 40,
+            "mscale": 1.0,
+            "mscale_all_dim": 1.0,
+            "original_max_position_embeddings": 4096,
+            "type": "yarn"
+        },
+        "residual_mlp": false,
+        "disable_weight_only_quant_plugin": false,
+        "moe": {
+            "num_experts": 256,
+            "shared_expert_intermediate_size": 2048,
+            "top_k": 8,
+            "normalization_mode": 3,
+            "sparse_mixer_epsilon": 0.01,
+            "tp_mode": 0,
+            "topk_method": 2,
+            "device_limited_n_group": 8,
+            "device_limited_topk_group": 4,
+            "device_limited_routed_scaling_factor": 2.5
+        },
+        "remove_duplicated_kv_heads": false,
+        "fc_after_embed": false,
+        "use_input_layernorm_in_first_layer": true,
+        "use_last_layernorm": true,
+        "layer_idx_offset": 0,
+        "architecture": "DeepseekV3ForCausalLM",
+        "dtype": "bfloat16",
+        "vocab_size": 129280,
+        "hidden_size": 7168,
+        "num_hidden_layers": 61,
+        "num_attention_heads": 128,
+        "hidden_act": "swiglu",
+        "logits_dtype": "float32",
+        "norm_epsilon": 1e-06,
+        "runtime_defaults": null,
+        "position_embedding_type": "rope_gpt_neox",
+        "num_key_value_heads": 1,
+        "intermediate_size": 18432,
+        "max_position_embeddings": 163840,
+        "mapping": {
+            "world_size": 16,
+            "gpus_per_node": 8,
+            "cp_size": 1,
+            "tp_size": 16,
+            "pp_size": 1,
+            "moe_tp_size": 16,
+            "moe_ep_size": 1
+        },
+        "quantization": {
+            "quant_algo": "FP8_CURRENT_SCALING",
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": 0.5,
+            "clamp_val": null,
+            "use_meta_recipe": false,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "head_size": 576,
+        "qk_layernorm": false,
+        "rotary_embedding_dim": 576,
+        "moe_inter_size": 2048,
+        "kv_lora_rank": 512,
+        "q_lora_rank": 1536,
+        "qk_nope_head_dim": 128,
+        "qk_rope_head_dim": 64,
+        "v_head_dim": 128,
+        "topk_method": "noaux_tc",
+        "first_k_dense_replace": 3,
+        "moe_layer_freq": 1,
+        "coring_func": "sigmoid",
+        "fp8_format": false
+    },
+    "build_config": {
+        "max_input_len": 16192,
+        "max_seq_len": 32000,
+        "opt_batch_size": 8,
+        "max_batch_size": 64,
+        "max_beam_width": 1,
+        "max_num_tokens": 8192,
+        "opt_num_tokens": 64,
+        "max_prompt_embedding_table_size": 0,
+        "kv_cache_type": "PAGED",
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "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": "H100-PCIe",
+            "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": "bfloat16",
+            "bert_attention_plugin": "auto",
+            "gpt_attention_plugin": "auto",
+            "gemm_plugin": null,
+            "gemm_swiglu_plugin": null,
+            "fp8_rowwise_gemm_plugin": null,
+            "fp8_current_scaling_gemm_plugin": "bfloat16",
+            "qserve_gemm_plugin": null,
+            "identity_plugin": null,
+            "nccl_plugin": "bfloat16",
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "smooth_quant_plugins": true,
+            "smooth_quant_gemm_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": "auto",
+            "mamba_conv1d_plugin": "auto",
+            "low_latency_gemm_plugin": null,
+            "low_latency_gemm_swiglu_plugin": null,
+            "context_fmha": true,
+            "bert_context_fmha_fp32_acc": false,
+            "paged_kv_cache": true,
+            "remove_input_padding": true,
+            "reduce_fusion": false,
+            "user_buffer": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": true,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": false,
+            "streamingllm": false,
+            "manage_weights": false,
+            "use_fused_mlp": true,
+            "pp_reduce_scatter": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1024,
+        "use_fused_mlp": true,
+        "monitor_memory": false,
+        "use_mrope": false
+    }
+}

rank0.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee990e5083fce3084aa51a531dcda221c12c94c19d8a75d84f4f4ebfef0fecb
+size 45241570500

rank1.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa3e6eb1ce722246c8aa2c05dd0a4578ae873ffeb7e3de7b0e7986d85e23082
+size 45241570500

rank10.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2efc13dba3b2ab84d65d594a071bdaaf1a963b7d0820edfe804c66494d440bea
+size 45241570500

rank11.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d888ea80fa70a9d4f2898b175089ebd86d9444ab9de415fd595ba0cba1da578
+size 45241570500

rank12.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb042bf7fefe5c2bf5a64929f5230a2c9e38ef8f77fb54087b6e2719c300a3e
+size 45241570500

rank13.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:eaec810c54f13f7a9bac739aea9657090f973f945e71d43f78bcf9f78e9fb08c
+size 45241570500

rank14.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cdba3b68f5b8dffd5195d4c6233bfbf0d34a00941650f99299191ef42a8f7fdb
+size 45240762676

rank15.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1046042bbd7d2d2c6e09ea84210ab2d0df6195384009322cb208d12334dfa60f
+size 45240762676

rank2.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:288bd2b5b1222f344fd8f21105d0fdbcb63d0185c5f51f4b9a6a85c385312b12
+size 45241570500

rank3.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c40613654afea055c14984993f99b7d1adfef9d868a24af195b6a4bdf5f181
+size 45241570500

rank4.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cac3fc76adc31e94c380eae58dbc511c78ca8220a6e2ce836f5cb41e56256cea
+size 45241570500

rank5.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d49da674766b71f29772fd93852ea989eb272bfd042c4914a27f65e93ab243
+size 45241570500

rank6.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e5ea820463d40cc50e07887615f1845f2f761a34e2406ea2635cb3b8fb8300
+size 45241570500

rank7.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:49f7fcff643a0ba2c2d70a8f9d78c66c6666551d6b71fd8a68213c461c332d2c
+size 45241718340

rank8.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d050d41672ce8dca91729677db3889defacefc3973516e85e3eeaf717e33c356
+size 45241570500

rank9.engine ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd18dd3cd225e476eaec3cb3fb48fbf10aa16ce677284f419335e3c27200dd1
+size 45240762676