Commit
•
79515e1
1
Parent(s):
b8c2c9c
Upload MistralForCausalLM
Browse files- README.md +1 -1
- config.json +1 -1
- generation_config.json +3 -7
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +41 -41
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: mit
|
5 |
library_name: transformers
|
|
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- phi3
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
library_name: transformers
|
5 |
+
license: mit
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- phi3
|
config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"sliding_window": 2048,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32064
|
26 |
}
|
|
|
20 |
"sliding_window": 2048,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.43.0.dev0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32064
|
26 |
}
|
generation_config.json
CHANGED
@@ -1,11 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
-
"eos_token_id":
|
5 |
-
|
6 |
-
|
7 |
-
32007
|
8 |
-
],
|
9 |
-
"pad_token_id": 32009,
|
10 |
-
"transformers_version": "4.41.0"
|
11 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 32000,
|
5 |
+
"pad_token_id": 32000,
|
6 |
+
"transformers_version": "4.43.0.dev0"
|
|
|
|
|
|
|
|
|
7 |
}
|
model-00001-of-00002.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 sha256:3403fc7e50e4a23a265a54ee7c74c465be32dcf93371d5346d38b9a724f0546f
|
3 |
+
size 4991370968
|
model-00002-of-00002.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 sha256:79e3d00e5431b1b409d0222aea0daa244f715dc8a030b0dbc5e44be9b7353112
|
3 |
+
size 2650821816
|
model.safetensors.index.json
CHANGED
@@ -77,42 +77,42 @@
|
|
77 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
-
"model.layers.16.input_layernorm.weight": "model-
|
81 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
82 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
85 |
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
-
"model.layers.17.input_layernorm.weight": "model-
|
90 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
92 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
98 |
-
"model.layers.18.input_layernorm.weight": "model-
|
99 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
101 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
107 |
-
"model.layers.19.input_layernorm.weight": "model-
|
108 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
110 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-
|
113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-
|
115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-
|
116 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
117 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -122,23 +122,23 @@
|
|
122 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-
|
128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
134 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
135 |
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
138 |
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-
|
140 |
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
142 |
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
77 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
85 |
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
116 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
117 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
122 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
134 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
135 |
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
138 |
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|