Upload Qwen2MoeForCausalLM
Browse files- config.json +52 -0
- generation_config.json +9 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2-57B-A14B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2MoeForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"decoder_sparse_step": 1,
|
9 |
+
"eos_token_id": 151643,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 3584,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 18944,
|
14 |
+
"max_position_embeddings": 131072,
|
15 |
+
"max_window_layers": 28,
|
16 |
+
"mlp_only_layers": [],
|
17 |
+
"model_type": "qwen2_moe",
|
18 |
+
"moe_intermediate_size": 2560,
|
19 |
+
"norm_topk_prob": false,
|
20 |
+
"num_attention_heads": 28,
|
21 |
+
"num_experts": 64,
|
22 |
+
"num_experts_per_tok": 8,
|
23 |
+
"num_hidden_layers": 28,
|
24 |
+
"num_key_value_heads": 4,
|
25 |
+
"output_router_logits": false,
|
26 |
+
"quantization_config": {
|
27 |
+
"_load_in_4bit": true,
|
28 |
+
"_load_in_8bit": false,
|
29 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
30 |
+
"bnb_4bit_quant_storage": "uint8",
|
31 |
+
"bnb_4bit_quant_type": "nf4",
|
32 |
+
"bnb_4bit_use_double_quant": true,
|
33 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
34 |
+
"llm_int8_has_fp16_weight": false,
|
35 |
+
"llm_int8_skip_modules": null,
|
36 |
+
"llm_int8_threshold": 6.0,
|
37 |
+
"load_in_4bit": true,
|
38 |
+
"load_in_8bit": false,
|
39 |
+
"quant_method": "bitsandbytes"
|
40 |
+
},
|
41 |
+
"rms_norm_eps": 1e-06,
|
42 |
+
"rope_theta": 1000000.0,
|
43 |
+
"router_aux_loss_coef": 0.001,
|
44 |
+
"shared_expert_intermediate_size": 20480,
|
45 |
+
"sliding_window": 131072,
|
46 |
+
"tie_word_embeddings": false,
|
47 |
+
"torch_dtype": "bfloat16",
|
48 |
+
"transformers_version": "4.42.4",
|
49 |
+
"use_cache": true,
|
50 |
+
"use_sliding_window": false,
|
51 |
+
"vocab_size": 151936
|
52 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": [
|
4 |
+
151645,
|
5 |
+
151643
|
6 |
+
],
|
7 |
+
"pad_token_id": 151643,
|
8 |
+
"transformers_version": "4.42.4"
|
9 |
+
}
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a4096384088566bdae54b1bdc606ac41777e7f560edf1156807d6e6d0c2f857
|
3 |
+
size 4999814171
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a3d44b911d9526332b1064638c087771a9b0d28e78770dd9e1ae4fd28c458a0
|
3 |
+
size 5000701850
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ac313fb7a810ed9d86043c19fc374efd5033c1d5b5646b4962b4c670588b57c
|
3 |
+
size 4996266414
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:766c584830e547fc337133cc81e527a9c800e671e37517145c9a89a39f8ab23e
|
3 |
+
size 5000708468
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:270edc673b3392dc7b0ecc631c6d08e26b7e04d7ef694b7b1b3dcc88c2c7dfa3
|
3 |
+
size 4996267359
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e08da2759b9286bfd07e5b00e6971e19cf1b617b6c669d166692b5826503ce7
|
3 |
+
size 4999800814
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43847b67055c86f9fcb4da9bee2cc4ce71460e6f46a26702424cf988c4643c7f
|
3 |
+
size 1250055494
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|