Upload with huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,55 @@
+# Vicuna 13B V1.1 Chinese
+
+This model was obtained from following repo:
+* uukuguy/vicuna-13b-v1.1
+* ziqingyang/chinese-alpaca-lora-13b
+
+Merged using sciprts from: https://github.com/ymcui/Chinese-LLaMA-Alpaca
+
+Then quanized using following command (no act order):
+```
+python llama.py ~/Chinese-LLaMA-Alpaca/alpaca-combined-hf c4 \
+	--wbits 4 \
+	--true-sequential \
+	--groupsize 128 \
+	--save_safetensors vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors
+```
+
+Can confirm model output normal text, but question-answering quality is unknown
+
+
+# Vicuna Model Card
+
+## Model details
+
+**Model type:**
+Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Model date:**
+Vicuna was trained between March 2023 and April 2023.
+
+**Organizations developing the model:**
+The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
+
+**Paper or resources for more information:**
+https://vicuna.lmsys.org/
+
+**License:**
+Apache License 2.0
+
+**Where to send questions or comments about the model:**
+https://github.com/lm-sys/FastChat/issues
+
+## Intended use
+**Primary intended uses:**
+The primary use of Vicuna is research on large language models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+70K conversations collected from ShareGPT.com.
+
+## Evaluation dataset
+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

@@ -0,0 +1,55 @@
+# Vicuna 13B V1.1 Chinese
+
+This model was obtained from following repo:
+* uukuguy/vicuna-13b-v1.1
+* ziqingyang/chinese-alpaca-lora-13b
+
+Merged using sciprts from: https://github.com/ymcui/Chinese-LLaMA-Alpaca
+
+Then quanized using following command (no act order):
+```
+python llama.py ~/Chinese-LLaMA-Alpaca/alpaca-combined-hf c4 \
+	--wbits 4 \
+	--true-sequential \
+	--groupsize 128 \
+	--save_safetensors vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors
+```
+
+Can confirm model output normal text, but question-answering quality is unknown
+
+
+# Vicuna Model Card
+
+## Model details
+
+**Model type:**
+Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Model date:**
+Vicuna was trained between March 2023 and April 2023.
+
+**Organizations developing the model:**
+The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
+
+**Paper or resources for more information:**
+https://vicuna.lmsys.org/
+
+**License:**
+Apache License 2.0
+
+**Where to send questions or comments about the model:**
+https://github.com/lm-sys/FastChat/issues
+
+## Intended use
+**Primary intended uses:**
+The primary use of Vicuna is research on large language models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+70K conversations collected from ShareGPT.com.
+
+## Evaluation dataset
+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

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 49954
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
+size 757972

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d20613286fdb90b7974a199fdf441e579c63f0a4b328df14468cb56e5df877a
+size 7822495082