lrl-modelcloud
commited on
Commit
•
40c9d1a
1
Parent(s):
bd889f8
Upload folder using huggingface_hub (#1)
Browse files- 86eb3fc755e9cb4f355d5cca5985b4d3f6b512ccaaaa8dea3066247ceefb8fcd (9d7f4aad5c5fd623dec394bc8596e85249434118)
- 16548ba68d0f6f1eaebc2eeb136287cf52a8f055cb333d80363311d20c17ad0a (4371989c228be9308507ff77019d4570afbd5437)
- config.json +44 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quantize_config.json +17 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/model/Mistal-Nemo-Instruct-2407/",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 1024000,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"quantization_config": {
|
20 |
+
"bits": 4,
|
21 |
+
"checkpoint_format": "gptq",
|
22 |
+
"damp_percent": 0.01,
|
23 |
+
"desc_act": true,
|
24 |
+
"group_size": 128,
|
25 |
+
"lm_head": false,
|
26 |
+
"meta": {
|
27 |
+
"quantizer": "gptqmodel:0.9.9-dev0"
|
28 |
+
},
|
29 |
+
"model_file_base_name": null,
|
30 |
+
"model_name_or_path": null,
|
31 |
+
"quant_method": "gptq",
|
32 |
+
"static_groups": false,
|
33 |
+
"sym": true,
|
34 |
+
"true_sequential": true
|
35 |
+
},
|
36 |
+
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"sliding_window": null,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"torch_dtype": "bfloat16",
|
41 |
+
"transformers_version": "4.43.0.dev0",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 131072
|
44 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eb4a7514c177c4599aa1cac588b8e881abf6494c2aa523f731822301960273b
|
3 |
+
size 8357951944
|
quantize_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"static_groups": false,
|
6 |
+
"sym": true,
|
7 |
+
"lm_head": false,
|
8 |
+
"damp_percent": 0.01,
|
9 |
+
"true_sequential": true,
|
10 |
+
"model_name_or_path": "",
|
11 |
+
"model_file_base_name": "model",
|
12 |
+
"quant_method": "gptq",
|
13 |
+
"checkpoint_format": "gptq",
|
14 |
+
"meta": {
|
15 |
+
"quantizer": "gptqmodel:0.9.9-dev0"
|
16 |
+
}
|
17 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|