初始化项目，由ModelHub XC社区提供模型

Model: second-state/NeuralBeagle14-7B-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,48 @@
+*.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
+*.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralBeagle14-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

NeuralBeagle14-7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eeeb0e87eef8a45a6a350d7696dbc703b56dc85b77b4120e30622e96d2afe60
+size 2719242176

NeuralBeagle14-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea8c52f163b731b2a58372d4e5ee9d8d48d82db431f0c2b976aecbd9ebc5535
+size 3822024640

NeuralBeagle14-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceca7b74d9eb13263aaeb250272d2781266ea35b3a3da63b96d974af93f9f7f5
+size 3518986176

NeuralBeagle14-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ab207ce4bf7d0ac6065e6662639bc74f1373f07f975303df36984281aac130
+size 3164567488

NeuralBeagle14-7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd76233f8c9005cfbecca607a935af5cf3cb816a423e71f5cc57ac7c2b3e166
+size 4108916672

NeuralBeagle14-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a3ff7a1e8ab7847fba496997c2795b1d014f2b140266fb479285b5dda06305
+size 4368439232

NeuralBeagle14-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b957af6eb014c73313fb6dff3f444e89b2a905b600edc688cb94aa402cdb4f
+size 4140373952

NeuralBeagle14-7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5f4d566aa3f159c432ed4cfc949b0e258176479a09ee080ad375c3f211f31f
+size 4997715904

NeuralBeagle14-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece9a1f43b7029a1a67e3abd56dbf7231fd40f5aa983deb278ecddf84cbe6907
+size 5131409344

NeuralBeagle14-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c698e9c0ff569ddb14c2b42e709e17ca0aebe655c6352a334c27f4ce2b2a7d24
+size 4997715904

NeuralBeagle14-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7225150aaebff90fa718a4736706df105e8d9df46a456a291a3e09c03cdc57e0
+size 5942065088

NeuralBeagle14-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cf8f0ff33bfa4bbf2b4e4d1412d8115e8c0a993d840cd59b3f11d614b9556f
+size 7695857600

README.md

@@ -0,0 +1,83 @@
+---
+base_model: mlabonne/NeuralBeagle14-7B
+inference: false
+license: apache-2.0
+model_creator: Maxime Labonne
+model_name: NeuralBeagle14 7B
+model_type: mistral
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+tags:
+- merge
+- mergekit
+- lazymergekit
+- fblgit/UNA-TheBeagle-7b-v1
+- argilla/distilabeled-Marcoro14-7B-slerp
+- dpo
+- rlhf
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# NeuralBeagle14-7B-GGUF
+
+## Original Model
+
+[mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
+
+## Run with LlamaEdge
+
+Note that the original model has an potential issue (see the discussion: [Model follows ChatML format, but does not have the special tokens for ChatML](https://huggingface.co/mlabonne/NeuralBeagle14-7B/discussions/3)).
+
+<!-- - LlamaEdge version: [v0.2.8](https://github.com/second-state/LlamaEdge/releases/tag/0.2.8) and above
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+- Context size: `4096`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:NeuralBeagle14-7B-Q5_K_M.gguf llama-api-server.wasm -p chatml
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:NeuralBeagle14-7B-Q5_K_M.gguf llama-chat.wasm -p chatml
+  ``` -->
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [NeuralBeagle14-7B-Q2_K.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q2_K.gguf)     | Q2_K   | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes |
+| [NeuralBeagle14-7B-Q3_K_L.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss |
+| [NeuralBeagle14-7B-Q3_K_M.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss |
+| [NeuralBeagle14-7B-Q3_K_S.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss |
+| [NeuralBeagle14-7B-Q4_0.ggufs](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q4_0.gguf)     | Q4_0   | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [NeuralBeagle14-7B-Q4_K_M.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended |
+| [NeuralBeagle14-7B-Q4_K_S.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss |
+| [NeuralBeagle14-7B-Q5_0.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q5_0.gguf)     | Q5_0   | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [NeuralBeagle14-7B-Q5_K_M.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended |
+| [NeuralBeagle14-7B-Q5_K_S.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended |
+| [NeuralBeagle14-7B-Q6_K.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q6_K.gguf)     | Q6_K   | 6 | 5.94 GB| very large, extremely low quality loss |
+| [NeuralBeagle14-7B-Q8_0.gguf](https://huggingface.co/second-state/NeuralBeagle14-7B-GGUF/blob/main/NeuralBeagle14-7B-Q8_0.gguf)     | Q8_0   | 8 | 7.70 GB| very large, extremely low quality loss - not recommended |

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mlabonne/Beagle14-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}