初始化项目，由ModelHub XC社区提供模型

Model: cortexso/tinyllama
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- cortex.cpp
+---
+
+## Overview
+
+The [TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned  on a diverse range of synthetic dialogues generated by ChatGPT.
+
+## Variants
+
+| No | Variant | Cortex CLI command |
+| --- | --- | --- |
+| 1 | [TinyLLama-1b](https://huggingface.co/cortexso/tinyllama/tree/1b) | `cortex run tinyllama:1b` |
+
+
+## Use it with Jan (UI)
+
+1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
+2. Use in Jan model Hub:
+    ```bash
+    cortexhub/tinyllama
+    ```
+    
+## Use it with Cortex (CLI)
+
+1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
+2. Run the model with command:
+    ```bash
+    cortex run tinyllama
+    ```
+    
+## Credits
+
+- **Author:** Microsoft
+- **Converter:** [Homebrew](https://www.homebrew.ltd/)
+- **Original License:** [License](https://choosealicense.com/licenses/apache-2.0/)
+- **Papers:** [Tinyllama Paper](https://arxiv.org/abs/2401.02385)

configuration.json

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

metadata.yml

@@ -0,0 +1,5 @@
+# metadata.yml
+version: 1
+name: tinyllama
+default: 1b
+author: "TinyLlama"

model.yml

@@ -0,0 +1,19 @@
+name: tinyllama 1B
+model: tinyllama:1B
+version: 1
+
+# Results Preferences
+stop:
+  - </s>
+top_p: 0.95
+temperature: 0.7
+frequency_penalty: 0
+presence_penalty: 0
+max_tokens: 4096 # Infer from base config.json -> max_position_embeddings
+stream: true # true | false
+
+# Engine / Model Settings
+ngl: 33 # Infer from base config.json -> num_attention_heads
+ctx_len: 4096 # Infer from base config.json -> max_position_embeddings
+engine: llama-cpp
+prompt_template: "\n\n<|system|>\n{system_message}</s>\n\n\n\n\n<|user|>\n{prompt}</s>\n\n\n<|assistant|>\n\n"

tinyllama-1.1b-chat-v1.0-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8772cdbfa36d507796117a5354447f6095092938482f52a180c9653ae9878ec2
+size 432132160

tinyllama-1.1b-chat-v1.0-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac85193e7af88af22f14507954e25bc6cceba198a2fd5e6a182ab784892beb22
+size 591528000

tinyllama-1.1b-chat-v1.0-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ce0e53200f1962456198e2a6d470d646d6013ec045b40b574d065d4d7519c4
+size 548405312

tinyllama-1.1b-chat-v1.0-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db4606b81830612f54b2dde753defc596406867b4017ad248ca3acda84584b2
+size 499343424

tinyllama-1.1b-chat-v1.0-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571d0894f55da36ecbee9d76ce548cb9230a5eefeb324e1432410f0001b8426e
+size 667816000

tinyllama-1.1b-chat-v1.0-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670c7049f88de39854a3c8c6899e768c8ef65a3e299804a3373ede8aeae10961
+size 639873088

tinyllama-1.1b-chat-v1.0-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afe9da14312109d94fbf28c5f6fa2503e2c4dfa8920dfe0125bf93601aba978
+size 782045248

tinyllama-1.1b-chat-v1.0-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c763261d767c198969e08ce36de5c5ed4d2c53a78e54e40a321f246a5902fe
+size 766029888

tinyllama-1.1b-chat-v1.0-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d3e093b4d353e4330c2f1e7c39ef2e9fd6698c90d231e0db43956bb69a542b
+size 903413824

tinyllama-1.1b-chat-v1.0-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ebb0e87a4ca41b22aee08eb04c27dd5efa75b517ff38d12bb801685de4680b
+size 1169809472