初始化项目，由ModelHub XC社区提供模型

Model: bastienp/Gemma-2-2B-Instruct-structured-output
Source: Original Platform

.gitattributes

@@ -0,0 +1,40 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+base_model: google/gemma-2-2b-it
+language:
+- en
+license: gemma
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- gemma2
+datasets:
+- paraloq/json_data_extraction
+library_name: peft
+---
+
+# Gemma-2 2B Instruct fine-tuned on JSON dataset
+
+This model is a Gemma-2 2b model fine-tuned to paraloq/json_data_extraction.
+
+The model has been fine-tuned to extract data from a text according to a json schema.
+## Prompt
+
+The prompt used during training is:
+```py
+"""Below is a text paired with input that provides further context. Write JSON output that matches the schema to extract information.
+
+### Input:
+{input}
+
+### Schema:
+{schema}
+
+### Response:
+"""
+```
+
+## Using the Model
+
+You can use the model with the transformer library or with the wrapper from [unsloth] (https://unsloth.ai/blog/gemma2), which allows faster inference.
+
+```py
+import torch
+from unsloth import FastLanguageModel
+
+# Required to avoid cache size exceeded
+torch._dynamo.config.accumulated_cache_size_limit = 2048
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = f"bastienp/Gemma-2-2B-it-JSON-data-extration",
+    max_seq_length = 2048,
+    dtype = torch.float16,
+    load_in_4bit = False,
+    token = HF_TOKEN_READ,
+)
+```
+
+## Using the Quantized model (llama.cpp)
+
+The model is supplied in GGFU format in 4bit and 8bit.
+
+Example code with Llamacpp:
+```py
+from llama_cpp import Llama
+
+llm = Llama.from_pretrained(
+    "bastienp/Gemma-2-2B-it-JSON-data-extration",
+    filename="*Q4_K_M.gguf", #*Q8_K_M.gguf for the 8 bit version
+    verbose=False,
+)
+```
+
+The base model used for fine-tuning is google/gemma-2-2b-it. This repository is **NOT** affiliated with Google.
+
+Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms. 
+
+- **Developed by:** bastienp
+- **License:** gemma
+- **Finetuned from model :** google/gemma-2-2b-it

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-2-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b7a94a247bf8e76c3be868e18903f58b2fc426452807914de41aad2f424fb0
+size 25586896

config.json

@@ -0,0 +1,3 @@
+{
+    "model_type": "gemma2"
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

unsloth.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11acb9f91e502dc0ac9d9c2b15b56603abf5d6d7ff73d29b35c0646ff77d6f49
+size 5235213824

unsloth.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f2514772816db14bacb9fa0c14e8ba793608e6d083b652735ab702fac4707b
+size 1708582400

unsloth.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a011f30f463d89f52a602367a4a1ba8a6465249551bd6797030198c0b5204571
+size 1923278336

unsloth.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b521af3434cce9ca5320402505da9eb8b1cd3beb65de82a72f3c63f372f762ac
+size 2784495104