Training in progress, step 5
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- config.json +17 -1
- training_args.bin +2 -2
adapter_config.json
CHANGED
@@ -10,23 +10,23 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"q_proj",
|
25 |
"down_proj",
|
26 |
"v_proj",
|
27 |
"gate_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
"q_proj",
|
25 |
"down_proj",
|
26 |
"v_proj",
|
27 |
"gate_proj",
|
28 |
+
"k_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d12353c1855093797242a7acd2cc466785232351ab795a6e39be6d0eda00a926
|
3 |
+
size 83945296
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"_name_or_path": "unsloth/Meta-Llama-3.1-8B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
@@ -20,6 +21,21 @@
|
|
20 |
"num_key_value_heads": 8,
|
21 |
"pad_token_id": 128004,
|
22 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"rms_norm_eps": 1e-05,
|
24 |
"rope_scaling": {
|
25 |
"factor": 8.0,
|
@@ -31,7 +47,7 @@
|
|
31 |
"rope_theta": 500000.0,
|
32 |
"tie_word_embeddings": false,
|
33 |
"torch_dtype": "bfloat16",
|
34 |
-
"transformers_version": "4.
|
35 |
"unsloth_version": "2024.9",
|
36 |
"use_cache": false,
|
37 |
"vocab_size": 128256
|
|
|
1 |
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
"_name_or_path": "unsloth/Meta-Llama-3.1-8B",
|
4 |
"architectures": [
|
5 |
"LlamaForCausalLM"
|
|
|
21 |
"num_key_value_heads": 8,
|
22 |
"pad_token_id": 128004,
|
23 |
"pretraining_tp": 1,
|
24 |
+
"quantization_config": {
|
25 |
+
"_load_in_4bit": false,
|
26 |
+
"_load_in_8bit": true,
|
27 |
+
"bnb_4bit_compute_dtype": "float32",
|
28 |
+
"bnb_4bit_quant_storage": "uint8",
|
29 |
+
"bnb_4bit_quant_type": "fp4",
|
30 |
+
"bnb_4bit_use_double_quant": false,
|
31 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
32 |
+
"llm_int8_has_fp16_weight": false,
|
33 |
+
"llm_int8_skip_modules": null,
|
34 |
+
"llm_int8_threshold": 6.0,
|
35 |
+
"load_in_4bit": false,
|
36 |
+
"load_in_8bit": true,
|
37 |
+
"quant_method": "bitsandbytes"
|
38 |
+
},
|
39 |
"rms_norm_eps": 1e-05,
|
40 |
"rope_scaling": {
|
41 |
"factor": 8.0,
|
|
|
47 |
"rope_theta": 500000.0,
|
48 |
"tie_word_embeddings": false,
|
49 |
"torch_dtype": "bfloat16",
|
50 |
+
"transformers_version": "4.46.0",
|
51 |
"unsloth_version": "2024.9",
|
52 |
"use_cache": false,
|
53 |
"vocab_size": 128256
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc4c339d5730e6ec9d0d548b10a92b6b67b7c212c9d1c201a554ed13523e0a6
|
3 |
+
size 6712
|