Hugging Face's logo

Alpha-VLLM
/
MoE-Mixtral-7B-8Expert

Model card Files Community
Enderfga commited on
Commit
f625e3e
•
1 Parent(s): ecdf188

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. finetuned/sg/ultrachat200kWizardcode/config.json +19 -0
  2. finetuned/sg/ultrachat200kWizardcode/consolidated.00-of-08.model.pth +3 -0
  3. finetuned/sg/ultrachat200kWizardcode/consolidated.01-of-08.model.pth +3 -0
  4. finetuned/sg/ultrachat200kWizardcode/consolidated.02-of-08.model.pth +3 -0
  5. finetuned/sg/ultrachat200kWizardcode/consolidated.03-of-08.model.pth +3 -0
  6. finetuned/sg/ultrachat200kWizardcode/consolidated.04-of-08.model.pth +3 -0
  7. finetuned/sg/ultrachat200kWizardcode/consolidated.05-of-08.model.pth +3 -0
  8. finetuned/sg/ultrachat200kWizardcode/consolidated.06-of-08.model.pth +3 -0
  9. finetuned/sg/ultrachat200kWizardcode/consolidated.07-of-08.model.pth +3 -0
  10. finetuned/sg/ultrachat200kWizardcode/meta.json +3 -0
  11. finetuned/sg/ultrachat200kWizardcode/tokenizer.model +3 -0
finetuned/sg/ultrachat200kWizardcode/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 4096,
3
+ "hidden_dim": 14336,
4
+ "head_dim": 128,
5
+ "n_layers": 32,
6
+ "n_heads": 32,
7
+ "n_kv_heads": 8,
8
+ "vocab_size": 32000,
9
+ "norm_eps": 1e-05,
10
+ "rope_theta": 1000000,
11
+ "max_batch_size": 32,
12
+ "max_seq_len": 4096,
13
+ "moe": {
14
+ "num_experts_per_tok": 2,
15
+ "num_experts": 8
16
+ },
17
+ "load_balancing_weight": 0.1,
18
+ "rope_scaling": null
19
+ }
finetuned/sg/ultrachat200kWizardcode/consolidated.00-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db59e4e7be41627b98a7400eed6a4932c0d8cbcb7ed0d8b02997002ca849b08
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.01-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43816f2e7c6783702eb01cd476728718768b36818b635910b6fab9c024a2d8c7
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.02-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52199cf752fdec5ddfc295e008dea31157de14eab9801586cc73d15d7c5ec63c
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.03-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afaabbd3563d0653a49a38a7e5548d48aca788a979857128cd74054175797737
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.04-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44037021825fd176c986755a198b16994c6476c00132a99ea421026660d2f5f
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.05-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30fae8fe136a525f6c1cf72de32c0e4ae77f8d4fad661b229411756029e38957
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.06-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5dbf37b601cc285929119a05b085b2ac78c2e4d01e13d9b16cbee0984418bb
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/consolidated.07-of-08.model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed02050d5b6941e12a74884ce7e47cafb7fe8ecdc8a0d6a33c78f709bb2ba2a2
3
+ size 11678110239
finetuned/sg/ultrachat200kWizardcode/meta.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "llama_type": "mistral"
3
+ }
finetuned/sg/ultrachat200kWizardcode/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443