Hugging Face's logo

ExAi
/
dolphin-2.9-llama3-MoE-4x70B

Text Generation
Transformers
Safetensors
English
mixtral
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Biskwit commited on
Commit
e90cb98
•
1 Parent(s): f8a377e

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +33 -0
  2. model-00001-of-00049.safetensors +3 -0
  3. model-00002-of-00049.safetensors +3 -0
  4. model-00003-of-00049.safetensors +3 -0
  5. model-00004-of-00049.safetensors +3 -0
  6. model-00005-of-00049.safetensors +3 -0
  7. model-00006-of-00049.safetensors +3 -0
  8. model-00007-of-00049.safetensors +3 -0
  9. model-00008-of-00049.safetensors +3 -0
  10. model-00009-of-00049.safetensors +3 -0
  11. model-00010-of-00049.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2.9-llama3-70b",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128256,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 64,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 4,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 500000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.36.2",
31
+ "use_cache": false,
32
+ "vocab_size": 128258
33
+ }
model-00001-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189933d4e4b887608d2375e612437d13b3f494d7e29fef0cd3712afaafbef68b
3
+ size 9751858608
model-00002-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523ec183cf65da8de4b5542f5b0a8b4093ca7a4cfe0db45f66bb7a1df7e025d5
3
+ size 9697266968
model-00003-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dad3717bcf36d6e4a503e68b683e3b05aa1c3ed7ae472f1a720ea74c92d22e9
3
+ size 9999290320
model-00004-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9c96e551fe60db55a2cf81793ca0eb87be1d447b5bbba0b356b70b07214287
3
+ size 9999290320
model-00005-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40755e9971ce2a86dc8b4dcc78a24cf1d3ae50fe658fdf16744109d598e4190a
3
+ size 9697266968
model-00006-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc2e9c93eef6193abb8a323253094be7aa537ff81f8ffc88f257b1c9e88823c
3
+ size 9999290320
model-00007-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db20fbb72a630d9a79024072aa1d1f10d09c8eeeefd2cf6188ad7356a4e95e8
3
+ size 9999290344
model-00008-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c022f90dd9874034a7a1c7d0e814180771e86b9d3bd7b3615664a24180f7b2
3
+ size 9697266992
model-00009-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1046bbdea8b2682b834dd2ecf582313b20f26cc07c8dcb557f935433401ea4
3
+ size 9999290352
model-00010-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:601ef216621a2b25dcbf68128074e44cbdfe288c23f31962f242ceda92b7111b
3
+ size 9999290352
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff