Upload Qwen2MoeForCausalLM
Browse files- config.json +52 -0
- generation_config.json +14 -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-Instruct",
|
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": 32768,
|
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": 65536,
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.42.4"
|
14 |
+
}
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:013fcfb3c9c73c2287141751f1468b4898d554be23dd45944f058a40a411971a
|
3 |
+
size 4999814138
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cc20e3a4f28a19818c385f693f68394b91e86f2c671df349067751346c3f2bd
|
3 |
+
size 5000701839
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:678ff4174c266d2761778c7992f666754d87f22d0316701cc00c4addfae45a68
|
3 |
+
size 4996266411
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08abc48c9236e2150de0504899a5a4c750d80c832d0f574b81c428ba2878b297
|
3 |
+
size 5000708490
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8450ffa67712359de28827a8b510f38574e121578c196e78342d65dc362f36
|
3 |
+
size 4996267363
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:325184cb1d3160cbd6ce384d0103a3bab2f10275d6d64ed9fca588b6e740fcc1
|
3 |
+
size 4999800839
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9800f042da7217fb6605c5fe9202d5c8c29bc9fdef7229f72b0a195a3b286779
|
3 |
+
size 1250055496
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|