michimalek
commited on
Commit
•
1be2419
1
Parent(s):
0064b9d
Upload model
Browse files- adapter_config.json +25 -38
- adapter_model.safetensors +3 -0
adapter_config.json
CHANGED
@@ -1,40 +1,27 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
|
10 |
-
"hidden_size": 4096,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 14336,
|
13 |
-
"max_position_embeddings": 32768,
|
14 |
-
"model_type": "mistral",
|
15 |
-
"num_attention_heads": 32,
|
16 |
-
"num_hidden_layers": 32,
|
17 |
-
"num_key_value_heads": 8,
|
18 |
-
"quantization_config": {
|
19 |
-
"_load_in_4bit": true,
|
20 |
-
"_load_in_8bit": false,
|
21 |
-
"bnb_4bit_compute_dtype": "float16",
|
22 |
-
"bnb_4bit_quant_type": "nf4",
|
23 |
-
"bnb_4bit_use_double_quant": false,
|
24 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
-
"llm_int8_has_fp16_weight": false,
|
26 |
-
"llm_int8_skip_modules": null,
|
27 |
-
"llm_int8_threshold": 6.0,
|
28 |
-
"load_in_4bit": true,
|
29 |
-
"load_in_8bit": false,
|
30 |
-
"quant_method": "bitsandbytes"
|
31 |
-
},
|
32 |
-
"rms_norm_eps": 1e-05,
|
33 |
-
"rope_theta": 1000000.0,
|
34 |
-
"sliding_window": null,
|
35 |
-
"tie_word_embeddings": false,
|
36 |
-
"torch_dtype": "float16",
|
37 |
-
"transformers_version": "4.38.1",
|
38 |
-
"use_cache": true,
|
39 |
-
"vocab_size": 32000
|
40 |
-
}
|
|
|
1 |
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 64,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj"
|
23 |
],
|
24 |
+
"task_type": "CAUSAL_LM",
|
25 |
+
"use_dora": false,
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cc15c959fe55635898842974f3e42da1c8fbf5b954e74afb5bc1563873ca091
|
3 |
+
size 33563048
|