e6812b1247
* draft model.json * islm3b update * capybara 34b update * deepseek coder update * dolphin yi update * fix the maxtokens of islm * lzlv 70b update * marx3b update * mythomax 13b update * update neural chat 7b * noromaid 20b update * update openchat 7b * openhermes7b update * openorca 7b * orca 13b update * phind 34b update * rocket 3b update * starling 7b update * storytelling 70b update * tiefighter 13B * update tiefighter tags * tinyllama update * wizard coder 13b * update wizard coder 13b description * wizard coder 34b update * wizard coder minor fix * xwin 70b update * yarn 70b * yi 34b * zephyr beta 7b * neuralhermes-7b update * change path + ctxlen * update id * fix startling
21 lines
690 B
JSON
21 lines
690 B
JSON
{
|
|
"source_url": "https://huggingface.co/TheBloke/Yarn-Llama-2-70B-32k-GGUF/resolve/main/yarn-llama-2-70b-32k.Q5_K_M.gguf",
|
|
"id": "yarn-70b",
|
|
"object": "model",
|
|
"name": "Yarn 32k 70B",
|
|
"version": "1,0",
|
|
"description": "Yarn-Llama-2-70b-32k is designed specifically for handling long contexts. It represents an extension of the Llama-2-70b-hf model, now supporting a 32k token context window.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 4096
|
|
},
|
|
"parameters": {
|
|
"max_tokens": 4096
|
|
},
|
|
"metadata": {
|
|
"author": "NousResearch, The Bloke",
|
|
"tags": ["General Use", "Big Context Length"],
|
|
"size": 48750000000
|
|
}
|
|
}
|
|
|