Hugging Face's logo

altomek
/
Euryale-1.3-L2-70B-4.15bpw-EXL2

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
Inference Endpoints
4-bit precision
exl2
Model card Files Community
altomek commited on
Commit
4e2ee25
•
1 Parent(s): c0e1e25

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +37 -37
config.json CHANGED
@@ -1,38 +1,38 @@
1
- {
2
- "_name_or_path": "/workspace/Euryale-1.3-L2-70B",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 8192,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 28672,
13
- "max_position_embeddings": 4096,
14
- "model_type": "llama",
15
- "num_attention_heads": 64,
16
- "num_hidden_layers": 80,
17
- "num_key_value_heads": 8,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "rope_theta": 10000.0,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "float16",
24
- "transformers_version": "4.34.0",
25
- "use_cache": true,
26
- "vocab_size": 32000,
27
- "quantization_config": {
28
- "quant_method": "exl2",
29
- "version": "0.1.0",
30
- "bits": 4.15,
31
- "head_bits": 8,
32
- "calibration": {
33
- "rows": 100,
34
- "length": 2048,
35
- "dataset": "(default)"
36
- }
37
- }
38
  }
 
1
+ {
2
+ "_name_or_path": "/workspace/Euryale-1.3-L2-70B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.34.0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.1.0",
30
+ "bits": 4,
31
+ "head_bits": 8,
32
+ "calibration": {
33
+ "rows": 100,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
  }