Upload 10 files
Browse files- config.json +4 -4
- generation_config.json +1 -0
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +2 -2
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +11 -11
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
CHANGED
@@ -1,12 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "ifuseok/sft-solar-10.7b-
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
-
"eos_token_id":
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
@@ -16,6 +15,7 @@
|
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 48,
|
18 |
"num_key_value_heads": 8,
|
|
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
@@ -24,5 +24,5 @@
|
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": false,
|
27 |
-
"vocab_size":
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "ifuseok/sft-solar-10.7b-v1.1",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
|
|
7 |
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 48,
|
17 |
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 2,
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
|
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": false,
|
27 |
+
"vocab_size": 32000
|
28 |
}
|
generation_config.json
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
|
|
5 |
"transformers_version": "4.34.1",
|
6 |
"use_cache": false
|
7 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 2,
|
6 |
"transformers_version": "4.34.1",
|
7 |
"use_cache": false
|
8 |
}
|
model-00001-of-00003.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:e88527c86783c60a55a7e42cfb6250721ab64f7adf3ccd99f4cb4ecade66e1d6
|
3 |
+
size 9942981696
|
model-00002-of-00003.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 sha256:915d1745a194f6628b932d4ac8e08d8df46bdbb667ad1da0f1abff885c5ddba1
|
3 |
+
size 9999621616
|
model-00003-of-00003.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:f0a8309a88b412642c68849aed72ad9e938834edac0646777b5262ebc1349766
|
3 |
+
size 1520495544
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
@@ -145,10 +145,10 @@
|
|
145 |
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
146 |
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
147 |
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
152 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
153 |
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
154 |
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
@@ -356,11 +356,11 @@
|
|
356 |
"model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
357 |
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
358 |
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
359 |
-
"model.layers.44.input_layernorm.weight": "model-
|
360 |
-
"model.layers.44.mlp.down_proj.weight": "model-
|
361 |
"model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
362 |
"model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
363 |
-
"model.layers.44.post_attention_layernorm.weight": "model-
|
364 |
"model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
365 |
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
366 |
"model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
@@ -370,10 +370,10 @@
|
|
370 |
"model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
371 |
"model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
372 |
"model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
373 |
-
"model.layers.45.self_attn.k_proj.weight": "model-
|
374 |
"model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
375 |
-
"model.layers.45.self_attn.q_proj.weight": "model-
|
376 |
-
"model.layers.45.self_attn.v_proj.weight": "model-
|
377 |
"model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
378 |
"model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
379 |
"model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 21463048192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
145 |
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
146 |
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
147 |
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
152 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
153 |
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
154 |
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
356 |
"model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
357 |
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
358 |
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
359 |
+
"model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
361 |
"model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
362 |
"model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
364 |
"model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
365 |
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
366 |
"model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
370 |
"model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
371 |
"model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
372 |
"model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
374 |
"model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
377 |
"model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
378 |
"model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
379 |
"model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
special_tokens_map.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|