Upload LlamaForCausalLM
Browse files- config.json +1 -1
- 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 +1 -10
config.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"max_position_embeddings": 32768,
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
-
"num_hidden_layers":
|
18 |
"num_key_value_heads": 8,
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
|
|
14 |
"max_position_embeddings": 32768,
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b479a9aafb0fa6e3062c7d864a07628c99faf8e3e37cb9c0800330fa05a8ce3e
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e06f9a6d24fecb328632236fec322a849bfb6419d40eb5405fdb327542d096
|
3 |
size 4999819336
|
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:b5d8bd27dcb1dbaa61bdbfe5ad7f77fdd5427d875b76dee5caeafc679fad8753
|
3 |
+
size 4540516344
|
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",
|
@@ -239,15 +239,6 @@
|
|
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.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
243 |
-
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
244 |
-
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
245 |
-
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
246 |
-
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
247 |
-
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
248 |
-
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
249 |
-
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
250 |
-
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
251 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
"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",
|
|
|
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",
|