mwalol commited on
Commit
d57b382
·
verified ·
1 Parent(s): 474ce67

Upload model

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "custom_pipelines": {
10
+ "text-generation": {
11
+ "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
12
+ "pt": "AutoModelForCausalLM"
13
+ }
14
+ },
15
+ "eos_token_id": 32014,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 2048,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 5504,
20
+ "max_position_embeddings": 16384,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 24,
24
+ "num_key_value_heads": 16,
25
+ "pad_token_id": 32014,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "factor": 4.0,
30
+ "type": "linear"
31
+ },
32
+ "rope_theta": 100000,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "float16",
35
+ "transformers_version": "4.36.1",
36
+ "use_cache": true,
37
+ "vocab_size": 32256
38
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32014,
5
+ "pad_token_id": 32014,
6
+ "transformers_version": "4.36.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efd8d924374abd9d0da2aae6fabb77469689673ee26993edee44fa387467100
3
+ size 2692968904