Commit
•
501c1f2
1
Parent(s):
a06d254
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- config.json +47 -0
- llama_float16_tp2_rank0.engine +3 -0
- llama_float16_tp2_rank1.engine +3 -0
- model.cache +0 -0
.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 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"builder_config": {
|
3 |
+
"fp8": false,
|
4 |
+
"hidden_act": "silu",
|
5 |
+
"hidden_size": 8192,
|
6 |
+
"int8": false,
|
7 |
+
"max_batch_size": 8,
|
8 |
+
"max_input_len": 2048,
|
9 |
+
"max_num_tokens": null,
|
10 |
+
"max_output_len": 512,
|
11 |
+
"max_position_embeddings": 4096,
|
12 |
+
"name": "llama",
|
13 |
+
"num_heads": 64,
|
14 |
+
"num_kv_heads": 8,
|
15 |
+
"num_layers": 80,
|
16 |
+
"parallel_build": false,
|
17 |
+
"pipeline_parallel": 1,
|
18 |
+
"precision": "float16",
|
19 |
+
"quant_mode": 33,
|
20 |
+
"tensor_parallel": 2,
|
21 |
+
"use_refit": false,
|
22 |
+
"vocab_size": 32000
|
23 |
+
},
|
24 |
+
"plugin_config": {
|
25 |
+
"attention_qk_half_accumulation": false,
|
26 |
+
"bert_attention_plugin": false,
|
27 |
+
"context_fmha_type": 1,
|
28 |
+
"gemm_plugin": "float16",
|
29 |
+
"gpt_attention_plugin": "float16",
|
30 |
+
"identity_plugin": false,
|
31 |
+
"layernorm_plugin": false,
|
32 |
+
"layernorm_quantization_plugin": false,
|
33 |
+
"lookup_plugin": false,
|
34 |
+
"nccl_plugin": "float16",
|
35 |
+
"paged_kv_cache": false,
|
36 |
+
"quantize_per_token_plugin": false,
|
37 |
+
"quantize_tensor_plugin": false,
|
38 |
+
"remove_input_padding": true,
|
39 |
+
"rmsnorm_plugin": false,
|
40 |
+
"rmsnorm_quantization_plugin": false,
|
41 |
+
"smooth_quant_gemm_plugin": false,
|
42 |
+
"tokens_per_block": 0,
|
43 |
+
"use_custom_all_reduce": false,
|
44 |
+
"weight_only_groupwise_quant_matmul_plugin": "float16",
|
45 |
+
"weight_only_quant_matmul_plugin": false
|
46 |
+
}
|
47 |
+
}
|
llama_float16_tp2_rank0.engine
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75488f564582b9856b4c31ece6ab4e24df662ec0961f46dba1fd70d41f244108
|
3 |
+
size 18261991260
|
llama_float16_tp2_rank1.engine
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59d366ece059bb046c18644b72adc88bde251e4d32bff944d8738fc0d0ffc5e3
|
3 |
+
size 18261991260
|
model.cache
ADDED
Binary file (372 kB). View file
|
|