Upload MistralForCausalLM
Browse files- config.json +2 -2
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +10 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -12,7 +12,7 @@
|
|
12 |
"max_position_embeddings": 32768,
|
13 |
"model_type": "mistral",
|
14 |
"num_attention_heads": 32,
|
15 |
-
"num_hidden_layers":
|
16 |
"num_key_value_heads": 8,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
"rope_theta": 10000.0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bruins-rp",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
12 |
"max_position_embeddings": 32768,
|
13 |
"model_type": "mistral",
|
14 |
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 8,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
"rope_theta": 10000.0,
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:856cbe3f4ec9f41a8523bf64c7f9cdec4b188e615136fe96f7a3822c4d77c9e6
|
3 |
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec97b4b65e5b76303b33215211d5ab87fbd1b031351cfccef906b0ff2b97c356
|
3 |
size 4999819232
|
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 sha256:12ac8df8e0ccf4f23628aaf88ae4e685ca7ea587e45b6b18cd48c9d7994fdb12
|
3 |
+
size 4540516256
|
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",
|
@@ -230,6 +230,15 @@
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
233 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
234 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
235 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|