jfiekdjdk commited on
Commit
641041e
1 Parent(s): dc2d6a5

Upload with huggingface_hub

Browse files
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Vicuna 13B V1.1 Chinese
2
+
3
+ This model was obtained from following repo:
4
+ * uukuguy/vicuna-13b-v1.1
5
+ * ziqingyang/chinese-alpaca-lora-13b
6
+
7
+ Merged using sciprts from: https://github.com/ymcui/Chinese-LLaMA-Alpaca
8
+
9
+ Then quanized using following command (no act order):
10
+ ```
11
+ python llama.py ~/Chinese-LLaMA-Alpaca/alpaca-combined-hf c4 \
12
+ --wbits 4 \
13
+ --true-sequential \
14
+ --groupsize 128 \
15
+ --save_safetensors vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors
16
+ ```
17
+
18
+ Can confirm model output normal text, but question-answering quality is unknown
19
+
20
+
21
+ # Vicuna Model Card
22
+
23
+ ## Model details
24
+
25
+ **Model type:**
26
+ Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
27
+ It is an auto-regressive language model, based on the transformer architecture.
28
+
29
+ **Model date:**
30
+ Vicuna was trained between March 2023 and April 2023.
31
+
32
+ **Organizations developing the model:**
33
+ The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
34
+
35
+ **Paper or resources for more information:**
36
+ https://vicuna.lmsys.org/
37
+
38
+ **License:**
39
+ Apache License 2.0
40
+
41
+ **Where to send questions or comments about the model:**
42
+ https://github.com/lm-sys/FastChat/issues
43
+
44
+ ## Intended use
45
+ **Primary intended uses:**
46
+ The primary use of Vicuna is research on large language models and chatbots.
47
+
48
+ **Primary intended users:**
49
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
50
+
51
+ ## Training dataset
52
+ 70K conversations collected from ShareGPT.com.
53
+
54
+ ## Evaluation dataset
55
+ A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Vicuna 13B V1.1 Chinese
2
+
3
+ This model was obtained from following repo:
4
+ * uukuguy/vicuna-13b-v1.1
5
+ * ziqingyang/chinese-alpaca-lora-13b
6
+
7
+ Merged using sciprts from: https://github.com/ymcui/Chinese-LLaMA-Alpaca
8
+
9
+ Then quanized using following command (no act order):
10
+ ```
11
+ python llama.py ~/Chinese-LLaMA-Alpaca/alpaca-combined-hf c4 \
12
+ --wbits 4 \
13
+ --true-sequential \
14
+ --groupsize 128 \
15
+ --save_safetensors vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors
16
+ ```
17
+
18
+ Can confirm model output normal text, but question-answering quality is unknown
19
+
20
+
21
+ # Vicuna Model Card
22
+
23
+ ## Model details
24
+
25
+ **Model type:**
26
+ Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
27
+ It is an auto-regressive language model, based on the transformer architecture.
28
+
29
+ **Model date:**
30
+ Vicuna was trained between March 2023 and April 2023.
31
+
32
+ **Organizations developing the model:**
33
+ The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
34
+
35
+ **Paper or resources for more information:**
36
+ https://vicuna.lmsys.org/
37
+
38
+ **License:**
39
+ Apache License 2.0
40
+
41
+ **Where to send questions or comments about the model:**
42
+ https://github.com/lm-sys/FastChat/issues
43
+
44
+ ## Intended use
45
+ **Primary intended uses:**
46
+ The primary use of Vicuna is research on large language models and chatbots.
47
+
48
+ **Primary intended users:**
49
+ The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
50
+
51
+ ## Training dataset
52
+ 70K conversations collected from ShareGPT.com.
53
+
54
+ ## Evaluation dataset
55
+ A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 5120,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 13824,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 40,
14
+ "num_hidden_layers": 40,
15
+ "pad_token_id": 0,
16
+ "rms_norm_eps": 1e-06,
17
+ "tie_word_embeddings": false,
18
+ "torch_dtype": "float16",
19
+ "transformers_version": "4.28.0",
20
+ "use_cache": true,
21
+ "vocab_size": 49954
22
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.0"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
3
+ size 757972
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d20613286fdb90b7974a199fdf441e579c63f0a4b328df14468cb56e5df877a
3
+ size 7822495082