commit 279acb7d0c8268fda40156a4411b9166ed828f45 Author: ModelHub XC Date: Tue Jul 7 13:34:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: cortexso/llama3.2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..50988a2 --- /dev/null +++ b/README.md @@ -0,0 +1,41 @@ +--- +license: llama3.2 +pipeline_tag: text-generation +tags: +- cortex.cpp +- featured +--- + +## Overview + +Meta developed and released the [Meta Llama 3.2](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks. + +## Variants + +| No | Variant | Cortex CLI command | +| --- | --- | --- | +| 1 | [LLama3.2-1b](https://huggingface.co/cortexso/llama3.2/tree/1b) | `cortex run llama3.2:1b` | +| 2 | [LLama3.2-3b](https://huggingface.co/cortexso/llama3.2/tree/3b) | `cortex run llama3.2:3b` | + +## Use it with Jan (UI) + +1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) +2. Use in Jan model Hub: + ```bash + cortexso/llama3.2 + ``` + +## 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 llama3.2 + ``` + +## Credits + +- **Author:** Meta +- **Converter:** [Homebrew](https://www.homebrew.ltd/) +- **Original License:** [License](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt) +- **Papers:** [Llama-3.2 Blog](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/) \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/llama-3.2-1b-instruct-q2_k.gguf b/llama-3.2-1b-instruct-q2_k.gguf new file mode 100644 index 0000000..73438e1 --- /dev/null +++ b/llama-3.2-1b-instruct-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8132834c1b34d86dda3639d5ea4d27707ff0e5133aacaf840ea9021c8d0118b +size 580873984 diff --git a/llama-3.2-1b-instruct-q3_k_l.gguf b/llama-3.2-1b-instruct-q3_k_l.gguf new file mode 100644 index 0000000..a3f8294 --- /dev/null +++ b/llama-3.2-1b-instruct-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3028de333600b790fe5d2b97dcce98ef040ef224384e5090ce3facfad9eb904 +size 732524288 diff --git a/llama-3.2-1b-instruct-q3_k_m.gguf b/llama-3.2-1b-instruct-q3_k_m.gguf new file mode 100644 index 0000000..55bdf7e --- /dev/null +++ b/llama-3.2-1b-instruct-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d83717cd6fac5dcf5b1cd9bbfee7c1169906c67f217c07dacccde6f26d0ae4f +size 690843392 diff --git a/llama-3.2-1b-instruct-q3_k_s.gguf b/llama-3.2-1b-instruct-q3_k_s.gguf new file mode 100644 index 0000000..6b1824b --- /dev/null +++ b/llama-3.2-1b-instruct-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd8463e25d93d00ce190ad7f5545ec377e7975dd177076192bf1e1f0769ec89 +size 641691392 diff --git a/llama-3.2-1b-instruct-q4_k_m.gguf b/llama-3.2-1b-instruct-q4_k_m.gguf new file mode 100644 index 0000000..fcc0db4 --- /dev/null +++ b/llama-3.2-1b-instruct-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da937dbf4e3c9ad341a953132bd3dd40454ca989197a8fdd524be276bc193959 +size 807694080 diff --git a/llama-3.2-1b-instruct-q4_k_s.gguf b/llama-3.2-1b-instruct-q4_k_s.gguf new file mode 100644 index 0000000..730705b --- /dev/null +++ b/llama-3.2-1b-instruct-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f5358e6ae2a655cd03298b33c4285c514f6d4f81d46501ddc15d6c000676a7 +size 775646976 diff --git a/llama-3.2-1b-instruct-q5_k_m.gguf b/llama-3.2-1b-instruct-q5_k_m.gguf new file mode 100644 index 0000000..34309e6 --- /dev/null +++ b/llama-3.2-1b-instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54be289b5fcc860546f2fbf582bce65b80ee3fb432be7066e6963813c3ae57b +size 911503104 diff --git a/llama-3.2-1b-instruct-q5_k_s.gguf b/llama-3.2-1b-instruct-q5_k_s.gguf new file mode 100644 index 0000000..741ef45 --- /dev/null +++ b/llama-3.2-1b-instruct-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b4b8eceb0e1864c40c874be4eef4e82f5ac12595196fba015b12e6d670df6c +size 892563200 diff --git a/llama-3.2-1b-instruct-q6_k.gguf b/llama-3.2-1b-instruct-q6_k.gguf new file mode 100644 index 0000000..f9f73c2 --- /dev/null +++ b/llama-3.2-1b-instruct-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721e527e6979efc446480924adfd9e054308a0cefb692d91e54c552724cd259c +size 1021800192 diff --git a/llama-3.2-1b-instruct-q8_0.gguf b/llama-3.2-1b-instruct-q8_0.gguf new file mode 100644 index 0000000..6b83d1c --- /dev/null +++ b/llama-3.2-1b-instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a65b6ae0864a0090e0240918692ac56f356ed3cfbef469488540a6669aa4b7 +size 1321082624 diff --git a/llama-3.2-3b-instruct-q2_k.gguf b/llama-3.2-3b-instruct-q2_k.gguf new file mode 100644 index 0000000..60646ad --- /dev/null +++ b/llama-3.2-3b-instruct-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466a06cab337f08c0c86e4ff0449f2bfd38ed6ea024d5050b4d4fcd52fb2b718 +size 1363935392 diff --git a/llama-3.2-3b-instruct-q3_k_l.gguf b/llama-3.2-3b-instruct-q3_k_l.gguf new file mode 100644 index 0000000..64c0a95 --- /dev/null +++ b/llama-3.2-3b-instruct-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96be4e501efd989cea01571d21c6e96155638f5b11e7fa8c32430c5a257adf2c +size 1815347360 diff --git a/llama-3.2-3b-instruct-q3_k_m.gguf b/llama-3.2-3b-instruct-q3_k_m.gguf new file mode 100644 index 0000000..a9cad24 --- /dev/null +++ b/llama-3.2-3b-instruct-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51cd265abd299377d53490e996f17d2cac6861a207d176ef3449e1b54b6463ae +size 1687158944 diff --git a/llama-3.2-3b-instruct-q3_k_s.gguf b/llama-3.2-3b-instruct-q3_k_s.gguf new file mode 100644 index 0000000..8bdc9ac --- /dev/null +++ b/llama-3.2-3b-instruct-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da4bd1cc7059247db669ab8f12476e2d8520e9e9eface7c4e317f9a8173ac162 +size 1542848672 diff --git a/llama-3.2-3b-instruct-q4_k_m.gguf b/llama-3.2-3b-instruct-q4_k_m.gguf new file mode 100644 index 0000000..a02ec26 --- /dev/null +++ b/llama-3.2-3b-instruct-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c74731fcc92ee1b406ddc0a2f9992c8b7c29bb75e0e0950461a3a96c2129b96 +size 2019377312 diff --git a/llama-3.2-3b-instruct-q4_k_s.gguf b/llama-3.2-3b-instruct-q4_k_s.gguf new file mode 100644 index 0000000..dc9ac95 --- /dev/null +++ b/llama-3.2-3b-instruct-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3cfc202431e095dad632a751d4c793e331c165dff25c46ea7f8d894fffaa08 +size 1928200352 diff --git a/llama-3.2-3b-instruct-q5_k_m.gguf b/llama-3.2-3b-instruct-q5_k_m.gguf new file mode 100644 index 0000000..cd074f0 --- /dev/null +++ b/llama-3.2-3b-instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3430fc32253eee4e7eb27cfef711e3c061e5c8a18c939694fce0c801c85ad1 +size 2322153632 diff --git a/llama-3.2-3b-instruct-q5_k_s.gguf b/llama-3.2-3b-instruct-q5_k_s.gguf new file mode 100644 index 0000000..4da3a81 --- /dev/null +++ b/llama-3.2-3b-instruct-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b98a1355494e9eb69079ce6078aed758d7b16e10f2c909942d11f0fb75d41f +size 2269511840 diff --git a/llama-3.2-3b-instruct-q6_k.gguf b/llama-3.2-3b-instruct-q6_k.gguf new file mode 100644 index 0000000..29f531f --- /dev/null +++ b/llama-3.2-3b-instruct-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab075aecdcd250781ea8c3474ed25a9c4311adb14795f87252ee7b204f4dbc7 +size 2643853472 diff --git a/llama-3.2-3b-instruct-q8_0.gguf b/llama-3.2-3b-instruct-q8_0.gguf new file mode 100644 index 0000000..d178b48 --- /dev/null +++ b/llama-3.2-3b-instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:901d50753d2b0f68574e5448cff5271644aced613243efcf5d838b86a24f51be +size 3421898912 diff --git a/metadata.yml b/metadata.yml new file mode 100644 index 0000000..8fc4303 --- /dev/null +++ b/metadata.yml @@ -0,0 +1,5 @@ +# metadata.yml +version: 1 +name: llama3.2 +default: 3b +author: "meta-llama" \ No newline at end of file diff --git a/model.yml b/model.yml new file mode 100644 index 0000000..a8b805c --- /dev/null +++ b/model.yml @@ -0,0 +1,51 @@ +# BEGIN GENERAL GGUF METADATA +id: Llama-3.2-3B-Instruct # Model ID unique between models (author / quantization) +model: Llama-3.2-3B-Instruct # Model ID which is used for request construct - should be unique between models (author / quantization) +name: Llama-3.2-3B-Instruct # metadata.general.name +version: 2 # metadata.version + +# END GENERAL GGUF METADATA + +# BEGIN INFERENCE PARAMETERS +# BEGIN REQUIRED +stop: # tokenizer.ggml.eos_token_id + - <|eot_id|> +# END REQUIRED + +# BEGIN OPTIONAL +stream: true # Default true? +top_p: 0.9 # Ranges: 0 to 1 +temperature: 0.7 # Ranges: 0 to 1 +frequency_penalty: 0 # Ranges: 0 to 1 +presence_penalty: 0 # Ranges: 0 to 1 +max_tokens: 4096 # Should be default to context length +seed: -1 +dynatemp_range: 0 +dynatemp_exponent: 1 +top_k: 40 +min_p: 0.05 +tfs_z: 1 +typ_p: 1 +repeat_last_n: 64 +repeat_penalty: 1 +mirostat: false +mirostat_tau: 5 +mirostat_eta: 0.100000001 +penalize_nl: false +ignore_eos: false +n_probs: 0 +min_keep: 0 +# END OPTIONAL +# END INFERENCE PARAMETERS + +# BEGIN MODEL LOAD PARAMETERS +# BEGIN REQUIRED +engine: llama-cpp # engine to run model +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" +# END REQUIRED + +# BEGIN OPTIONAL +ctx_len: 4096 # llama.context_length | 0 or undefined = loaded from model +ngl: 29 # Undefined = loaded from model +# END OPTIONAL +# END MODEL LOAD PARAMETERS \ No newline at end of file