AutoGPTQ model for afkfatih/llama-2-7b-tr: 4bits, gr128, desc_act=False
Browse files- config.json +26 -0
- gptq_model-4bit-128g.bin +3 -0
- gptq_model-4bit-128g.safetensors +3 -0
- quantize_config.json +10 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "afkfatih/llama-2-7b-tr",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 32,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.31.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
gptq_model-4bit-128g.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e7985a10d558d37c9510a3714dcba492a69bd4272ec530814c4b9df5d4a9ce3
|
3 |
+
size 3897013783
|
gptq_model-4bit-128g.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bd612fe9a56c96cc7c89d6bf2f8506f6c90902ac915205a31ad36c0d0b5c0e9
|
3 |
+
size 3896726080
|
quantize_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"damp_percent": 0.01,
|
5 |
+
"desc_act": false,
|
6 |
+
"sym": true,
|
7 |
+
"true_sequential": true,
|
8 |
+
"model_name_or_path": "llama-2-7b-tr-4bit",
|
9 |
+
"model_file_base_name": "gptq_model-4bit-128g"
|
10 |
+
}
|