初始化项目，由ModelHub XC社区提供模型

Model: second-state/Bielik-1.5B-v3.0-Instruct-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
+Bielik-1.5B-v3.0-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-1.5B-v3.0-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Bielik-1.5B-v3.0-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18d1da61cbad31c9654f0e2307a9edca8cb35869182f511e2c8ff1f56b85f8d
+size 607284704

Bielik-1.5B-v3.0-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebebe962234b9ff72d13cb7c2c2a8fc32603d613f8a916d09276c26684814b2c
+size 845257184

Bielik-1.5B-v3.0-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb35dc9538e92416b5cb601d0711ab389097d06401726aa50bfc7e0e61a402c
+size 782735840

Bielik-1.5B-v3.0-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772411a6e3e297587375ef5807172100d13c2a81441908904e394cb90ad4cc0a
+size 709007840

Bielik-1.5B-v3.0-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24caa4825d594d571c531f89d3d0d251c7d0b9a39804175779d6387475a14e67
+size 914404832

Bielik-1.5B-v3.0-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9cc250a6c65718c290fd963d8e3237b924ccfc7632f20a6127bba5904a50d9
+size 972797408

Bielik-1.5B-v3.0-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adba06c51ff15cd7759ca79f34a73e84a105bb665f527343ab6d2362a733feb0
+size 921482720

Bielik-1.5B-v3.0-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a877fbbcbc70cd5b664605ae87eae1593d8cf51b9fd9dc4b7dec3c0bacf054
+size 1107719648

Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6ddbd18932ae34df487dc07532dba6fb5d4fac2cc1b66910e3565c556aec37
+size 1137800672

Bielik-1.5B-v3.0-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9325ce3ae23b31a6215a9b4befcaeea5a5775e89eeb9482bbd33b6f95b2301b
+size 1107719648

Bielik-1.5B-v3.0-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efef575f193cd06894ee9ecba9bea76f6fb05f3c86cbde16218e65e4a7f28916
+size 1313116640

Bielik-1.5B-v3.0-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c3ff5f451864151793476df8ad8364b8b23e2e6cd20de7a007eeeba10a8a3e
+size 1699568096

Bielik-1.5B-v3.0-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e379525b0871d7049136b0a2e8112cd348e89f6655323147d93ce0e21bf693
+size 3195509216

README.md

@@ -0,0 +1,86 @@
+---
+base_model: speakleash/Bielik-1.5B-v3.0-Instruct
+license: apache-2.0
+model_creator: speakleash
+model_name: Bielik-1.5B-v3.0-Instruct
+quantized_by: Second State Inc.
+language:
+- pl
+library_name: transformers
+inference:
+  parameters:
+    temperature: 0.4
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/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 -->
+
+# Bielik-1.5B-v3.0-Instruct-GGUF
+
+## Original Model
+
+[speakleash/Bielik-1.5B-v3.0-Instruct](https://huggingface.co/speakleash/Bielik-1.5B-v3.0-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.18.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.3)
+
+- 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: `8192`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Bielik-1.5B-v3.0-Instruct \
+    --prompt-template chatml \
+    --ctx-size 8192
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 8192
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Bielik-1.5B-v3.0-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 607 MB| smallest, significant quality loss - not recommended for most purposes |
+| [Bielik-1.5B-v3.0-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 845 MB| small, substantial quality loss |
+| [Bielik-1.5B-v3.0-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 783 MB| very small, high quality loss |
+| [Bielik-1.5B-v3.0-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 709 MB| very small, high quality loss |
+| [Bielik-1.5B-v3.0-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 914 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Bielik-1.5B-v3.0-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 973 MB| medium, balanced quality - recommended |
+| [Bielik-1.5B-v3.0-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 921 MB| small, greater quality loss |
+| [Bielik-1.5B-v3.0-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 1.11 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.14 GB| large, very low quality loss - recommended |
+| [Bielik-1.5B-v3.0-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.11 GB| large, low quality loss - recommended |
+| [Bielik-1.5B-v3.0-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 1.31 GB| very large, extremely low quality loss |
+| [Bielik-1.5B-v3.0-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 1.70 GB| very large, extremely low quality loss - not recommended |
+| [Bielik-1.5B-v3.0-Instruct-f16.gguf](https://huggingface.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF/blob/main/Bielik-1.5B-v3.0-Instruct-f16.gguf)       | f16    | 16 | 3.20 GB| |
+
+*Quantized with llama.cpp b5201*

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 4,
+  "pad_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 8192,
+  "mlp_bias": true,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}