richarderkhov/zardos_-_nil_llama-3-8b-instruct_v0.1.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nnil_Llama-3-8B-Instruct_v0.1.1 - GGUF\n- Model creator: https://huggingface.co/Zardos/\n- Original model: https://huggingface.co/Zardos/nil_Llama-3-8B-Instruct_v0.1.1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q2_K.gguf) | Q2_K | 2.96GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q3_K.gguf) | Q3_K | 3.74GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q4_K.gguf) | Q4_K | 4.58GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q5_K.gguf) | Q5_K | 5.34GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q6_K.gguf) | Q6_K | 6.14GB |\n| [nil_Llama-3-8B-Instruct_v0.1.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf/blob/main/nil_Llama-3-8B-Instruct_v0.1.1.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: apache-2.0\ntags:\n- text-generation-inference\n- transformers\n- llama3\n- llama\n- trl\nbase_model: unsloth/llama-3-8b-Instruct\n---\n\n\n# Uploaded  model\n\n- **Finetuned by:** Zardos\n- **License:** apache-2.0\n\n\n## How to use\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase.\n\n### Use with transformers\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.\n\n#### Transformers pipeline\n\n```python\nimport transformers\nimport torch\n\nmodel_id = \"meta-llama/Meta-Llama-3-8B-Instruct\"\n\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model_id,\n    model_kwargs={\"torch_dtype\": torch.bfloat16},\n    device_map=\"auto\",\n)\n\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are a pirate chatbot who always responds in pirate speak!\"},\n    {\"role\": \"user\", \"content\": \"Who are you?\"},\n]\n\nprompt = pipeline.tokenizer.apply_chat_template(\n\t\tmessages, \n\t\ttokenize=False, \n\t\tadd_generation_prompt=True\n)\n\nterminators = [\n    pipeline.tokenizer.eos_token_id,\n    pipeline.tokenizer.convert_tokens_to_ids(\"<|eot_id|>\")\n]\n\noutputs = pipeline(\n    prompt,\n    max_new_tokens=256,\n    eos_token_id=terminators,\n    do_sample=True,\n    temperature=0.6,\n    top_p=0.9,\n)\nprint(outputs[0][\"generated_text\"][len(prompt):])\n```\n\n#### Transformers AutoModelForCausalLM\n\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\nimport torch\n\nmodel_id = \"meta-llama/Meta-Llama-3-8B-Instruct\"\n\ntokenizer = AutoTokenizer.from_pretrained(model_id)\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_id,\n    torch_dtype=torch.bfloat16,\n    device_map=\"auto\",\n)\n\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are a pirate chatbot who always responds in pirate speak!\"},\n    {\"role\": \"user\", \"content\": \"Who are you?\"},\n]\n\ninput_ids = tokenizer.apply_chat_template(\n    messages,\n    add_generation_prompt=True,\n    return_tensors=\"pt\"\n).to(model.device)\n\nterminators = [\n    tokenizer.eos_token_id,\n    tokenizer.convert_tokens_to_ids(\"<|eot_id|>\")\n]\n\noutputs = model.generate(\n    input_ids,\n    max_new_tokens=256,\n    eos_token_id=terminators,\n    do_sample=True,\n    temperature=0.6,\n    top_p=0.9,\n)\nresponse = outputs[0][input_ids.shape[-1]:]\nprint(tokenizer.decode(response, skip_special_tokens=True))\n```\n\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 113,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-10T23:07:58.000Z",
  "created_at": "2024-10-10T20:17:23.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67083653da7c23b8856e59d9",
  "id": "RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf",
  "modelId": "RichardErkhov/Zardos_-_nil_Llama-3-8B-Instruct_v0.1.1-gguf",
  "sha": "f1a7748f989ebe1dd42d8ce3576a63c15d24da9b",
  "createdAt": "2024-10-10T20:17:23.000Z",
  "lastModified": "2024-10-10T23:07:58.000Z",
  "author": "RichardErkhov",
  "downloads": 113,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}