Occupying-Mars commited on
Commit
c78ac2a
1 Parent(s): 9572e8d

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llama_float16_tp2_rank0.engine filter=lfs diff=lfs merge=lfs -text
37
+ llama_float16_tp2_rank1.engine filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_config": {
3
+ "gather_all_token_logits": false,
4
+ "hidden_act": "swiglu",
5
+ "hidden_size": 4096,
6
+ "int8": false,
7
+ "lora_target_modules": [],
8
+ "max_batch_size": 8,
9
+ "max_beam_width": 1,
10
+ "max_input_len": 2048,
11
+ "max_num_tokens": null,
12
+ "max_output_len": 512,
13
+ "max_position_embeddings": 32768,
14
+ "max_prompt_embedding_table_size": 0,
15
+ "name": "llama",
16
+ "num_heads": 32,
17
+ "num_kv_heads": 8,
18
+ "num_layers": 32,
19
+ "parallel_build": true,
20
+ "pipeline_parallel": 1,
21
+ "precision": "float16",
22
+ "quant_mode": 0,
23
+ "tensor_parallel": 2,
24
+ "use_refit": false,
25
+ "vocab_size": 32002
26
+ },
27
+ "plugin_config": {
28
+ "attention_qk_half_accumulation": false,
29
+ "bert_attention_plugin": false,
30
+ "context_fmha_type": 1,
31
+ "gemm_plugin": false,
32
+ "gpt_attention_plugin": "float16",
33
+ "identity_plugin": false,
34
+ "layernorm_plugin": false,
35
+ "layernorm_quantization_plugin": false,
36
+ "lookup_plugin": false,
37
+ "lora_plugin": false,
38
+ "multi_block_mode": false,
39
+ "nccl_plugin": "float16",
40
+ "paged_kv_cache": true,
41
+ "quantize_per_token_plugin": false,
42
+ "quantize_tensor_plugin": false,
43
+ "remove_input_padding": true,
44
+ "rmsnorm_plugin": false,
45
+ "rmsnorm_quantization_plugin": false,
46
+ "smooth_quant_gemm_plugin": false,
47
+ "tokens_per_block": 128,
48
+ "use_context_fmha_for_generation": false,
49
+ "use_custom_all_reduce": false,
50
+ "use_paged_context_fmha": false,
51
+ "weight_only_groupwise_quant_matmul_plugin": false,
52
+ "weight_only_quant_matmul_plugin": false
53
+ }
54
+ }
llama_float16_tp2_rank0.engine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49400a103297acb964b1c65aca18ef879425326fc117abfe81cd145ea09c10ea
3
+ size 46842531828
llama_float16_tp2_rank1.engine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d559fcade958c0ef66bf98a480c054fae0cc6969cc09aac6d20b5dcfa9c6c5
3
+ size 46842531828
model.cache ADDED
Binary file (320 kB). View file