MatrixIA commited on
Commit
d618572
·
verified ·
1 Parent(s): 5384dd1

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +39 -31
config.json CHANGED
@@ -1,34 +1,42 @@
1
  {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
5
- "bias": "none",
6
- "fan_in_fan_out": false,
7
- "inference_mode": true,
8
- "init_lora_weights": true,
9
- "layer_replication": null,
10
- "layers_pattern": null,
11
- "layers_to_transform": null,
12
- "loftq_config": {},
13
- "lora_alpha": 16,
14
- "lora_dropout": 0,
15
- "megatron_config": null,
16
- "megatron_core": "megatron.core",
17
- "modules_to_save": null,
18
- "peft_type": "LORA",
19
- "r": 16,
20
- "rank_pattern": {},
21
- "revision": "unsloth",
22
- "target_modules": [
23
- "q_proj",
24
- "gate_proj",
25
- "up_proj",
26
- "v_proj",
27
- "k_proj",
28
- "o_proj",
29
- "down_proj"
30
  ],
31
- "task_type": "CAUSAL_LM",
32
- "use_dora": false,
33
- "use_rslora": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
 
1
  {
2
+ "_name_or_path": "MatrixIA/LLama-3-8B-SQL",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": true,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 500000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.38.2",
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
  }