matlok commited on
Commit
e09bf10
1 Parent(s): 5a5a8f1

initial release for the tinyllama merged model with 32k context: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T + Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct + Doctor-Shotgun/TinyLlama-1.1B-32k + Tensoic/TinyLlama-1.1B-3T-openhermes + Josephgflowers/TinyLlama-3T-Cinder-v1.3

Browse files
Files changed (3) hide show
  1. config.json +29 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "matlok/tinyllama-cinder-openhermes-32k",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.37.1",
26
+ "unsloth_version": "2024.1",
27
+ "use_cache": false,
28
+ "vocab_size": 32000
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.1",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb7be5c697e99c1fbf4bdc5531632e881e8f625d38da3a228daa96ae90ac6452
3
+ size 2200119664