Upload folder using huggingface_hub
Browse files- config.json +47 -0
- rank0.safetensors +3 -0
- rank1.safetensors +3 -0
- rank2.safetensors +3 -0
- rank3.safetensors +3 -0
- rank4.safetensors +3 -0
- rank5.safetensors +3 -0
- rank6.safetensors +3 -0
- rank7.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"producer": {
|
| 3 |
+
"name": "modelopt",
|
| 4 |
+
"version": "0.13.1"
|
| 5 |
+
},
|
| 6 |
+
"architecture": "LlamaForCausalLM",
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"logits_dtype": "float16",
|
| 9 |
+
"num_hidden_layers": 80,
|
| 10 |
+
"num_attention_heads": 64,
|
| 11 |
+
"num_key_value_heads": 8,
|
| 12 |
+
"hidden_size": 8192,
|
| 13 |
+
"norm_epsilon": 1e-05,
|
| 14 |
+
"vocab_size": 128256,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"use_parallel_embedding": true,
|
| 18 |
+
"embedding_sharding_dim": 0,
|
| 19 |
+
"quantization": {
|
| 20 |
+
"quant_algo": "FP8",
|
| 21 |
+
"kv_cache_quant_algo": "FP8"
|
| 22 |
+
},
|
| 23 |
+
"mapping": {
|
| 24 |
+
"world_size": 8,
|
| 25 |
+
"tp_size": 8,
|
| 26 |
+
"pp_size": 1
|
| 27 |
+
},
|
| 28 |
+
"head_size": 128,
|
| 29 |
+
"intermediate_size": 28672,
|
| 30 |
+
"position_embedding_type": "rope_gpt_neox",
|
| 31 |
+
"share_embedding_table": false,
|
| 32 |
+
"residual_mlp": false,
|
| 33 |
+
"bias": false,
|
| 34 |
+
"rotary_pct": 1.0,
|
| 35 |
+
"rank": 0,
|
| 36 |
+
"decoder": "llama",
|
| 37 |
+
"rmsnorm": true,
|
| 38 |
+
"lm_head_bias": false,
|
| 39 |
+
"rotary_base": 500000.0,
|
| 40 |
+
"rotary_scaling": {
|
| 41 |
+
"factor": 8.0,
|
| 42 |
+
"low_freq_factor": 1.0,
|
| 43 |
+
"high_freq_factor": 4.0,
|
| 44 |
+
"original_max_position_embeddings": 8192,
|
| 45 |
+
"rope_type": "llama3"
|
| 46 |
+
}
|
| 47 |
+
}
|
rank0.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf30a55b76219bc477b3d1acadb5784992f4796d3f5870d5c166ce84dcdeafc
|
| 3 |
+
size 9084523128
|
rank1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89eed6086a77cc4b93b8d35c9526f40b41603727b13c4ef22a856a29b8a8f5dc
|
| 3 |
+
size 9084523128
|
rank2.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d83d4d1fa3885582156e23034e51387353037a7d516d936139166634a1c197db
|
| 3 |
+
size 9084523128
|
rank3.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc296d5fc6ab6570e4ea8a8ad060d4852dc264ce0619d7bc7ac30be7ad178621
|
| 3 |
+
size 9084523128
|
rank4.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4c16f3cc05e1bf26d9f03a48d6d7de92ab751339bda2bbc01cc04a76b88abe5
|
| 3 |
+
size 9084523128
|
rank5.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:676fe53b528c1959db57217e0125c3459af7e52b6788b30a585549cd4aaca872
|
| 3 |
+
size 9084523128
|
rank6.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47904bdc3089e01fd1d512793e14ecd371ba1fc005850aea151a1f1fa8fad6b4
|
| 3 |
+
size 9084523128
|
rank7.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bd49ac7cb2885da1d554facd8f44a06b9166d26d5d2ce89445b6b326710716f
|
| 3 |
+
size 9084523128
|