PranavHarshan commited on
Commit
b04da53
·
verified ·
1 Parent(s): f912017

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +36 -0
  2. model-1.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ProbeMedicalYonseiMAILab/medllama3-v20",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "mixtral",
18
+ "num_attention_heads": 32,
19
+ "num_experts_per_tok": 2,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 8,
22
+ "num_local_experts": 2,
23
+ "output_router_logits": false,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 500000.0,
28
+ "router_aux_loss_coef": 0.001,
29
+ "router_jitter_noise": 0.0,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float16",
33
+ "transformers_version": "4.45.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
model-1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64a83db2d976c6716671ce514e73a2b0012b993caa31e0a2ec9965ca6edc787
3
+ size 1050681576