Training in progress, step 12
Browse files- FP16/adapter_config.json +5 -5
- FP16/adapter_model.safetensors +1 -1
- FP16/config.json +54 -0
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
FP16/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"down_proj",
|
25 |
-
"up_proj",
|
26 |
-
"gate_proj",
|
27 |
"v_proj",
|
28 |
"o_proj",
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
|
|
|
|
24 |
"v_proj",
|
25 |
"o_proj",
|
26 |
+
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"down_proj",
|
29 |
+
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
FP16/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d693e4b77d740670ba4486fba597e12e170bee8cd18c5d7f0b63d653a0b38a38
|
3 |
size 167832240
|
FP16/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 4096,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 14336,
|
18 |
+
"max_position_embeddings": 131072,
|
19 |
+
"mlp_bias": false,
|
20 |
+
"model_type": "llama",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"quantization_config": {
|
26 |
+
"_load_in_4bit": true,
|
27 |
+
"_load_in_8bit": false,
|
28 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
29 |
+
"bnb_4bit_quant_storage": "uint8",
|
30 |
+
"bnb_4bit_quant_type": "nf4",
|
31 |
+
"bnb_4bit_use_double_quant": true,
|
32 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
33 |
+
"llm_int8_has_fp16_weight": false,
|
34 |
+
"llm_int8_skip_modules": null,
|
35 |
+
"llm_int8_threshold": 6.0,
|
36 |
+
"load_in_4bit": true,
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"quant_method": "bitsandbytes"
|
39 |
+
},
|
40 |
+
"rms_norm_eps": 1e-05,
|
41 |
+
"rope_scaling": {
|
42 |
+
"factor": 8.0,
|
43 |
+
"high_freq_factor": 4.0,
|
44 |
+
"low_freq_factor": 1.0,
|
45 |
+
"original_max_position_embeddings": 8192,
|
46 |
+
"rope_type": "llama3"
|
47 |
+
},
|
48 |
+
"rope_theta": 500000.0,
|
49 |
+
"tie_word_embeddings": false,
|
50 |
+
"torch_dtype": "bfloat16",
|
51 |
+
"transformers_version": "4.43.4",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 128256
|
54 |
+
}
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"v_proj",
|
25 |
"o_proj",
|
26 |
"up_proj",
|
27 |
-
"k_proj",
|
28 |
"down_proj",
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"o_proj",
|
24 |
"up_proj",
|
|
|
25 |
"down_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e294bc7627a33d7909569424d0998e203d85f12a8dadb02254323e63ef93f2fc
|
3 |
size 167832240
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e9dee0397176cfee5a536de2a454ab26081d329cbae3f71150fb94d4f2aa8f
|
3 |
size 5496
|