lrl-modelcloud
commited on
Commit
•
08d88bd
1
Parent(s):
fffddf5
8c9d96b3288c06feb7f9dc8c83069d1b6f5bf6dc872c74533e36e96394997136
Browse files
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "/monster/data/model/Falcon3-10B-Instruct",
|
4 |
+
"architectures": [
|
5 |
+
"LlamaForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 11,
|
10 |
+
"eos_token_id": 11,
|
11 |
+
"head_dim": 256,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 3072,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 23040,
|
16 |
+
"max_position_embeddings": 32768,
|
17 |
+
"mlp_bias": false,
|
18 |
+
"model_type": "llama",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 40,
|
21 |
+
"num_key_value_heads": 4,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"quantization_config": {
|
24 |
+
"bits": 4,
|
25 |
+
"checkpoint_format": "gptq",
|
26 |
+
"desc_act": true,
|
27 |
+
"dynamic": null,
|
28 |
+
"group_size": 32,
|
29 |
+
"lm_head": false,
|
30 |
+
"meta": {
|
31 |
+
"damp_auto_increment": 0.0025,
|
32 |
+
"damp_percent": 0.1,
|
33 |
+
"mse": true,
|
34 |
+
"quantizer": [
|
35 |
+
"gptqmodel:1.4.4"
|
36 |
+
],
|
37 |
+
"static_groups": false,
|
38 |
+
"true_sequential": true,
|
39 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
40 |
+
},
|
41 |
+
"quant_method": "gptq",
|
42 |
+
"sym": true
|
43 |
+
},
|
44 |
+
"rms_norm_eps": 1e-06,
|
45 |
+
"rope_scaling": null,
|
46 |
+
"rope_theta": 1000042,
|
47 |
+
"tie_word_embeddings": false,
|
48 |
+
"torch_dtype": "bfloat16",
|
49 |
+
"transformers_version": "4.46.3",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 131072
|
52 |
+
}
|
model-00001-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24f555ef432d6ae0769c52267426ff0281df84607f476390dabd0a37603b3c16
|
3 |
+
size 805306504
|
model-00002-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c76085311451c0fb08b903b5c78bea86838061fce6058da315a9f7aad1c513b
|
3 |
+
size 6264
|
model-00003-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fac00788f7bf2a3f33a5087f341ad731a1817fdcdf814b798b8dddc6d2ea1a3d
|
3 |
+
size 805306496
|
model-00004-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bffe429715118bbba3d25894aa27c9230a258af076786ee3f3da9eab5520ad67
|
3 |
+
size 137487608
|
model-00005-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e50b7f8c12dd2ac741e7b0402ecb282c69f3e72c902717fbc72a131f7351c68
|
3 |
+
size 137487608
|
model-00006-of-00043.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d24de6323a566254aa4be2ebe6e4da3c55df2fb5c233f4675390d43b51fd7bf4
|
3 |
+
size 137487608
|