test

.gitattributes

@@ -33,14 +33,3 @@ saved_model/**/* 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
-model.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
-llama-3.1-8b-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,8 +1,5 @@
 ---
 license: llama3
-pipeline_tag: text-generation
-tags:
-- cortex.cpp
 ---
 
 ## Overview
@@ -13,13 +10,15 @@ Meta developed and released the [Meta Llama 3](https://huggingface.co/meta-llama
 
 | No | Variant | Cortex CLI command |
 | --- | --- | --- |
-| 1 | [Llama3-8b](https://huggingface.co/cortexso/llama3/tree/8b) | `cortex run llama3:8b` |
+| 1 | [onnx](https://huggingface.co/cortexso/llama3/tree/onnx) | `cortex run llama3:onnx` |
+| 2 | [gguf](https://huggingface.co/cortexso/llama3/tree/gguf) | `cortex run llama3:gguf` |
+| 3 | [default](https://huggingface.co/cortexso/llama3/tree/default) | `cortex run llama3` |
 
 ## Use it with Jan (UI)
 
 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
 2. Use in Jan model Hub:
-    ```bash
+    ```
     cortexso/llama3
     ```
 
@@ -27,7 +26,7 @@ Meta developed and released the [Meta Llama 3](https://huggingface.co/meta-llama
 
 1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
 2. Run the model with command:
-    ```bash
+    ```
     cortex run llama3
     ```
 

llama-3.1-8b-instruct-q2_k.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7ba07f0e6f20ed9a9a52c3a430dda0ab1c5eb71b5f61f194dbdb2691ad28bd94
-size 3179136256

llama-3.1-8b-instruct-q3_k_l.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0dec74f5fd617ad11172f763de849332254632248a430bd4b014971d12ae58a
-size 4321961216

llama-3.1-8b-instruct-q3_k_m.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85aac3fae4c469e566bfe7371ff67f143f6b7a99f347147da83479c379daed8d
-size 4018922752

llama-3.1-8b-instruct-q3_k_s.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:622914d9363361a6a24225cc1ccc5f952fe664517f1d2054dc84ab8fd3838017
-size 3664504064

llama-3.1-8b-instruct-q4_k_m.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c33f5a84eb2bbfbefcee9ec25cc8e639836eff6b1a54818774f254c18dbb4f5b
-size 4920739072

llama-3.1-8b-instruct-q4_k_s.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:24dd25091cde35e4c709dbcc4120430d0500fa2176dde27e67018967fb231f1f
-size 4692673792

llama-3.1-8b-instruct-q5_k_m.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0bf7159d0d4313a818da7270399ddcbb2dbfdb25d502b82e1680e40b55a1a7a7
-size 5732992256

llama-3.1-8b-instruct-q5_k_s.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ba5070018af5e009c832fbc90f7a7ab224b578be78fa7ada80c9e61ebbd39ec
-size 5599298816

llama-3.1-8b-instruct-q6_k.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4537e7b02653bfa7fe109ac917ac374bedf69cb15b9c6fea678cda4cb8de3b2
-size 6596011264

llama-3.1-8b-instruct-q8_0.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8349b563753acc025716792c2cad15de4f7e7ad5ea72a91f65c5df2bc226726f
-size 8540775680

metadata.yml

@@ -1,5 +0,0 @@
-# metadata.yml
-version: 1
-name: llama3
-default: 8b
-author: "meta-llama"

model.yml

@@ -1,23 +0,0 @@
-name: Llama 3
-model: llama3:8B
-version: 1
-
-# Results Preferences
-stop:
-  - <|end_of_text|>
-  - <|eot_id|>
-top_p: 0.95
-temperature: 0.7
-frequency_penalty: 0
-presence_penalty: 0
-max_tokens: 8192 # 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: 8192 # Infer from base config.json -> max_position_embeddings
-engine: llama-cpp
-prompt_template: "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
-# Prompt template: Can only be retrieved from instruct model
-# - https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/blob/main/tokenizer_config.json#L2053
-# - Requires jinja format parser