Upload LlamaForCausalLM
Browse files- config.json +2 -2
- generation_config.json +2 -2
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
- model-00004-of-00004.safetensors +2 -2
- model.safetensors.index.json +11 -11
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/output
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -24,5 +24,5 @@
|
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.40.0",
|
26 |
"use_cache": false,
|
27 |
-
"vocab_size":
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/__PEFT__/output",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.40.0",
|
26 |
"use_cache": false,
|
27 |
+
"vocab_size": 100290
|
28 |
}
|
generation_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
|
|
4 |
"eos_token_id": 128001,
|
5 |
-
"transformers_version": "4.40.0"
|
6 |
-
"use_cache": false
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
+
"do_sample": true,
|
5 |
"eos_token_id": 128001,
|
6 |
+
"transformers_version": "4.40.0"
|
|
|
7 |
}
|
model-00001-of-00004.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 sha256:2fd41cc3c98e42778cc2d30acf1b5770f495ddb6944c38ee0be464077db0297a
|
3 |
+
size 4948928368
|
model-00002-of-00004.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:cc70cac42a1a20102a8681347bff66d6b2a6ab0f0ecdfdba82cc2d0d44cfaeff
|
3 |
+
size 4915916168
|
model-00003-of-00004.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 sha256:30cb6a3c3e5aad28615fd291b2ea79a67ea9922db412b0dca834669328978abd
|
3 |
+
size 4915941072
|
model-00004-of-00004.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:b75672657c68183f4f1cde84a7aa352e98bb7db287e900a064e5621a6e17a384
|
3 |
+
size 821575808
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
@@ -125,7 +125,7 @@
|
|
125 |
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
129 |
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
130 |
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
@@ -230,11 +230,11 @@
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
235 |
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
238 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
@@ -286,13 +286,13 @@
|
|
286 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
288 |
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
289 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
290 |
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
291 |
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
292 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
293 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
294 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
295 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
296 |
-
"model.norm.weight": "model-
|
297 |
}
|
298 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 15602327552
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
|
|
125 |
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
129 |
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
130 |
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
235 |
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
238 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
|
|
286 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
288 |
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
290 |
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
291 |
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
297 |
}
|
298 |
}
|