Upload folder using huggingface_hub
#1
by
lrl-modelcloud
- opened
- config.json +66 -0
- model.safetensors +3 -0
- quantize_config.json +37 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/model/TinyLlama-1.1B-Chat-v1.0",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 22,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"quantization_config": {
|
22 |
+
"bits": 4,
|
23 |
+
"checkpoint_format": "gptq",
|
24 |
+
"damp_percent": 0.01,
|
25 |
+
"desc_act": true,
|
26 |
+
"group_size": 128,
|
27 |
+
"lm_head": false,
|
28 |
+
"meta": {
|
29 |
+
"amp": true,
|
30 |
+
"batch_size": 1,
|
31 |
+
"data_type": "int",
|
32 |
+
"dynamic_max_gap": -1,
|
33 |
+
"enable_full_range": false,
|
34 |
+
"enable_minmax_tuning": true,
|
35 |
+
"enable_quanted_input": true,
|
36 |
+
"gradient_accumulate_steps": 1,
|
37 |
+
"iters": 200,
|
38 |
+
"low_gpu_mem_usage": true,
|
39 |
+
"lr": null,
|
40 |
+
"lr_scheduler": null,
|
41 |
+
"minmax_lr": null,
|
42 |
+
"nblocks": 1,
|
43 |
+
"not_use_best_mse": false,
|
44 |
+
"nsamples": 512,
|
45 |
+
"quantizer": "gptqmodel:0.9.8-dev0",
|
46 |
+
"sampler": "rand",
|
47 |
+
"scale_dtype": "fp16",
|
48 |
+
"seed": 42,
|
49 |
+
"seqlen": 2048
|
50 |
+
},
|
51 |
+
"model_file_base_name": null,
|
52 |
+
"model_name_or_path": null,
|
53 |
+
"quant_method": "auto_round",
|
54 |
+
"static_groups": false,
|
55 |
+
"sym": true,
|
56 |
+
"true_sequential": true
|
57 |
+
},
|
58 |
+
"rms_norm_eps": 1e-05,
|
59 |
+
"rope_scaling": null,
|
60 |
+
"rope_theta": 10000.0,
|
61 |
+
"tie_word_embeddings": false,
|
62 |
+
"torch_dtype": "bfloat16",
|
63 |
+
"transformers_version": "4.43.0.dev0",
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 32000
|
66 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa590c869b52e9788c52646c6ba632afedf92752b0897d7ef369449b662fc7f2
|
3 |
+
size 767343824
|
quantize_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "auto_round",
|
13 |
+
"checkpoint_format": "gptq",
|
14 |
+
"meta": {
|
15 |
+
"quantizer": "gptqmodel:0.9.8-dev0",
|
16 |
+
"enable_full_range": false,
|
17 |
+
"batch_size": 1,
|
18 |
+
"amp": true,
|
19 |
+
"lr_scheduler": null,
|
20 |
+
"enable_quanted_input": true,
|
21 |
+
"enable_minmax_tuning": true,
|
22 |
+
"lr": null,
|
23 |
+
"minmax_lr": null,
|
24 |
+
"low_gpu_mem_usage": true,
|
25 |
+
"iters": 200,
|
26 |
+
"seqlen": 2048,
|
27 |
+
"nsamples": 512,
|
28 |
+
"sampler": "rand",
|
29 |
+
"seed": 42,
|
30 |
+
"nblocks": 1,
|
31 |
+
"gradient_accumulate_steps": 1,
|
32 |
+
"not_use_best_mse": false,
|
33 |
+
"dynamic_max_gap": -1,
|
34 |
+
"data_type": "int",
|
35 |
+
"scale_dtype": "fp16"
|
36 |
+
}
|
37 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": false,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|