Hugging Face's logo

lakkeo
/
stable-cypher-instruct-3b

Text Generation
Transformers
Safetensors
GGUF
English
stablelm
causal-lm
code
cypher
graph
neo4j
conversational
8-bit precision
bitsandbytes
Model card Files Community
lakkeo commited on
Commit
0904708
•
1 Parent(s): 5ad3a38

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +46 -46
config.json CHANGED
@@ -1,46 +1,46 @@
1
- {
2
- "_name_or_path": "stabilityai/stable-code-instruct-3b",
3
- "architectures": [
4
- "StableLmForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 0,
8
- "eos_token_id": 0,
9
- "hidden_act": "silu",
10
- "hidden_dropout": 0.0,
11
- "hidden_size": 2560,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 6912,
14
- "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 16384,
16
- "model_type": "stablelm",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 32,
19
- "num_key_value_heads": 32,
20
- "partial_rotary_factor": 0.25,
21
- "qk_layernorm": false,
22
- "quantization_config": {
23
- "_load_in_4bit": false,
24
- "_load_in_8bit": true,
25
- "bnb_4bit_compute_dtype": "float32",
26
- "bnb_4bit_quant_storage": "uint8",
27
- "bnb_4bit_quant_type": "fp4",
28
- "bnb_4bit_use_double_quant": false,
29
- "llm_int8_enable_fp32_cpu_offload": false,
30
- "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
32
- "llm_int8_threshold": 6.0,
33
- "load_in_4bit": false,
34
- "load_in_8bit": true,
35
- "quant_method": "bitsandbytes"
36
- },
37
- "rope_scaling": null,
38
- "rope_theta": 1000000,
39
- "tie_word_embeddings": false,
40
- "torch_dtype": "float32",
41
- "transformers_version": "4.41.2",
42
- "use_cache": false,
43
- "use_parallel_residual": false,
44
- "use_qkv_bias": false,
45
- "vocab_size": 50304
46
- }
 
1
+ {
2
+ "_name_or_path": "lakkeo/stable-cypher-instruct-3b",
3
+ "architectures": [
4
+ "StableLmForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "silu",
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 6912,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 16384,
16
+ "model_type": "stablelm",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "partial_rotary_factor": 0.25,
21
+ "qk_layernorm": false,
22
+ "quantization_config": {
23
+ "_load_in_4bit": false,
24
+ "_load_in_8bit": true,
25
+ "bnb_4bit_compute_dtype": "float32",
26
+ "bnb_4bit_quant_storage": "uint8",
27
+ "bnb_4bit_quant_type": "fp4",
28
+ "bnb_4bit_use_double_quant": false,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": false,
34
+ "load_in_8bit": true,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "rope_scaling": null,
38
+ "rope_theta": 1000000,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.41.2",
42
+ "use_cache": false,
43
+ "use_parallel_residual": false,
44
+ "use_qkv_bias": false,
45
+ "vocab_size": 50304
46
+ }