Upload 3 files
Browse files- gptq_model-4bit-128g.safetensors +3 -0
- model_config.json +16 -0
- tokenizer_config.json +0 -0
gptq_model-4bit-128g.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c31c40e8ff8f7c821ea68d5ede34ec63744d997224cc4ecd220e8461733e97ae
|
| 3 |
+
size 9125989024
|
model_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hidden_size": 5120,
|
| 3 |
+
"inner_hidden_size": 13696,
|
| 4 |
+
"head_hidden_size": 128,
|
| 5 |
+
"hidden_act": "silu",
|
| 6 |
+
"num_attention_heads": 40,
|
| 7 |
+
"num_key_value_heads": 40,
|
| 8 |
+
"num_layers": 40,
|
| 9 |
+
"qkv_bias": false,
|
| 10 |
+
"o_bias": false,
|
| 11 |
+
"vocab_size": 125696,
|
| 12 |
+
"dropout_rate": 0.0,
|
| 13 |
+
"layernorm_epsilon": 1e-06,
|
| 14 |
+
"max_sequence_length": 4096,
|
| 15 |
+
"use_alibi": true
|
| 16 |
+
}
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|