Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth

zetlyn/models-gguf quantisation gguf Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth hf meta-llama/Llama-3.2-3B-Instruct known 2026-09-14

https://huggingface.co/Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth

Properties

authorShankarblr
receipt
Source
GGUF quantisations
Its words
Shankarblr
Read by
field:author
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aa739b382b01847860448d1",
  "author": "Shankarblr",
  "cardData": {
    "base_model": "meta-llama/Llama-3.2-3B-Instruct",
    "base_model_relation": "finetune",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "metrics": [
      "loss"
    ],
    "model-index": [
      {
        "name": "Llama-3.2-3B-Unsloth-Instruct",
        "results": [
          {
            "dataset": {
              "name": "private ChatML SFT mix (10% holdout)",
              "split": "test",
              "type": "json"
            },
            "metrics": [
              {
                "name": "Eval loss (epoch 3)",
                "type": "loss",
                "value": 0.1614,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 2)",
                "type": "loss",
                "value": 0.1934,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 1)",
                "type": "loss",
                "value": 0.3627,
                "verified": false
              }
            ],
            "task": {
              "name": "Causal language modeling (teacher-forced eval)",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "llama",
      "llama-3.2",
      "unsloth",
      "qlora",
      "peft",
      "lora",
      "gguf",
      "semiconductor",
      "technical-writing",
      "product-brief",
      "datasheet",
      "user-guide"
    ]
  },
  "createdAt": "2026-09-14T00:02:59.000Z",
  "downloads": 5792,
  "gated": false,
  "id": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "lastModified": "2026-09-15T15:20:42.000Z",
  "library_name": "transformers",
  "likes": 1,
  "modelId": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "7d25743cfe34a261ceec61bf49c01ab80aac7685",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "chat_template.jinja"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "model-00001-of-00002.safetensors"
    },
    {
      "rfilename": "model-00002-of-00002.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "tags": [
    "transformers",
    "safetensors",
    "llama",
    "text-generation",
    "llama-3.2",
    "unsloth",
    "qlora",
    "peft",
    "lora",
    "gguf",
    "semiconductor",
    "technical-writing",
    "product-brief",
    "datasheet",
    "user-guide",
    "conversational",
    "en",
    "base_model:meta-llama/Llama-3.2-3B-Instruct",
    "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
    "license:llama3.2",
    "model-index",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ]
}
basemeta-llama/Llama-3.2-3B-Instruct
receipt
Source
GGUF quantisations
Its words
meta-llama/Llama-3.2-3B-Instruct
Read by
field:cardData.base_model[]
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aa739b382b01847860448d1",
  "author": "Shankarblr",
  "cardData": {
    "base_model": "meta-llama/Llama-3.2-3B-Instruct",
    "base_model_relation": "finetune",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "metrics": [
      "loss"
    ],
    "model-index": [
      {
        "name": "Llama-3.2-3B-Unsloth-Instruct",
        "results": [
          {
            "dataset": {
              "name": "private ChatML SFT mix (10% holdout)",
              "split": "test",
              "type": "json"
            },
            "metrics": [
              {
                "name": "Eval loss (epoch 3)",
                "type": "loss",
                "value": 0.1614,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 2)",
                "type": "loss",
                "value": 0.1934,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 1)",
                "type": "loss",
                "value": 0.3627,
                "verified": false
              }
            ],
            "task": {
              "name": "Causal language modeling (teacher-forced eval)",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "llama",
      "llama-3.2",
      "unsloth",
      "qlora",
      "peft",
      "lora",
      "gguf",
      "semiconductor",
      "technical-writing",
      "product-brief",
      "datasheet",
      "user-guide"
    ]
  },
  "createdAt": "2026-09-14T00:02:59.000Z",
  "downloads": 5792,
  "gated": false,
  "id": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "lastModified": "2026-09-15T15:20:42.000Z",
  "library_name": "transformers",
  "likes": 1,
  "modelId": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "7d25743cfe34a261ceec61bf49c01ab80aac7685",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "chat_template.jinja"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "model-00001-of-00002.safetensors"
    },
    {
      "rfilename": "model-00002-of-00002.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "tags": [
    "transformers",
    "safetensors",
    "llama",
    "text-generation",
    "llama-3.2",
    "unsloth",
    "qlora",
    "peft",
    "lora",
    "gguf",
    "semiconductor",
    "technical-writing",
    "product-brief",
    "datasheet",
    "user-guide",
    "conversational",
    "en",
    "base_model:meta-llama/Llama-3.2-3B-Instruct",
    "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
    "license:llama3.2",
    "model-index",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ]
}
downloads5792
receipt
Source
GGUF quantisations
Its words
5792
Read by
field:downloads
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aa739b382b01847860448d1",
  "author": "Shankarblr",
  "cardData": {
    "base_model": "meta-llama/Llama-3.2-3B-Instruct",
    "base_model_relation": "finetune",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "metrics": [
      "loss"
    ],
    "model-index": [
      {
        "name": "Llama-3.2-3B-Unsloth-Instruct",
        "results": [
          {
            "dataset": {
              "name": "private ChatML SFT mix (10% holdout)",
              "split": "test",
              "type": "json"
            },
            "metrics": [
              {
                "name": "Eval loss (epoch 3)",
                "type": "loss",
                "value": 0.1614,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 2)",
                "type": "loss",
                "value": 0.1934,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 1)",
                "type": "loss",
                "value": 0.3627,
                "verified": false
              }
            ],
            "task": {
              "name": "Causal language modeling (teacher-forced eval)",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "llama",
      "llama-3.2",
      "unsloth",
      "qlora",
      "peft",
      "lora",
      "gguf",
      "semiconductor",
      "technical-writing",
      "product-brief",
      "datasheet",
      "user-guide"
    ]
  },
  "createdAt": "2026-09-14T00:02:59.000Z",
  "downloads": 5792,
  "gated": false,
  "id": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "lastModified": "2026-09-15T15:20:42.000Z",
  "library_name": "transformers",
  "likes": 1,
  "modelId": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "7d25743cfe34a261ceec61bf49c01ab80aac7685",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "chat_template.jinja"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "model-00001-of-00002.safetensors"
    },
    {
      "rfilename": "model-00002-of-00002.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "tags": [
    "transformers",
    "safetensors",
    "llama",
    "text-generation",
    "llama-3.2",
    "unsloth",
    "qlora",
    "peft",
    "lora",
    "gguf",
    "semiconductor",
    "technical-writing",
    "product-brief",
    "datasheet",
    "user-guide",
    "conversational",
    "en",
    "base_model:meta-llama/Llama-3.2-3B-Instruct",
    "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
    "license:llama3.2",
    "model-index",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ]
}
licencellama3.2
receipt
Source
GGUF quantisations
Its words
llama3.2
Read by
field:cardData.license
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aa739b382b01847860448d1",
  "author": "Shankarblr",
  "cardData": {
    "base_model": "meta-llama/Llama-3.2-3B-Instruct",
    "base_model_relation": "finetune",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "metrics": [
      "loss"
    ],
    "model-index": [
      {
        "name": "Llama-3.2-3B-Unsloth-Instruct",
        "results": [
          {
            "dataset": {
              "name": "private ChatML SFT mix (10% holdout)",
              "split": "test",
              "type": "json"
            },
            "metrics": [
              {
                "name": "Eval loss (epoch 3)",
                "type": "loss",
                "value": 0.1614,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 2)",
                "type": "loss",
                "value": 0.1934,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 1)",
                "type": "loss",
                "value": 0.3627,
                "verified": false
              }
            ],
            "task": {
              "name": "Causal language modeling (teacher-forced eval)",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "llama",
      "llama-3.2",
      "unsloth",
      "qlora",
      "peft",
      "lora",
      "gguf",
      "semiconductor",
      "technical-writing",
      "product-brief",
      "datasheet",
      "user-guide"
    ]
  },
  "createdAt": "2026-09-14T00:02:59.000Z",
  "downloads": 5792,
  "gated": false,
  "id": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "lastModified": "2026-09-15T15:20:42.000Z",
  "library_name": "transformers",
  "likes": 1,
  "modelId": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "7d25743cfe34a261ceec61bf49c01ab80aac7685",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "chat_template.jinja"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "model-00001-of-00002.safetensors"
    },
    {
      "rfilename": "model-00002-of-00002.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "tags": [
    "transformers",
    "safetensors",
    "llama",
    "text-generation",
    "llama-3.2",
    "unsloth",
    "qlora",
    "peft",
    "lora",
    "gguf",
    "semiconductor",
    "technical-writing",
    "product-brief",
    "datasheet",
    "user-guide",
    "conversational",
    "en",
    "base_model:meta-llama/Llama-3.2-3B-Instruct",
    "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
    "license:llama3.2",
    "model-index",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ]
}
likes1
receipt
Source
GGUF quantisations
Its words
1
Read by
field:likes
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aa739b382b01847860448d1",
  "author": "Shankarblr",
  "cardData": {
    "base_model": "meta-llama/Llama-3.2-3B-Instruct",
    "base_model_relation": "finetune",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "llama3.2",
    "metrics": [
      "loss"
    ],
    "model-index": [
      {
        "name": "Llama-3.2-3B-Unsloth-Instruct",
        "results": [
          {
            "dataset": {
              "name": "private ChatML SFT mix (10% holdout)",
              "split": "test",
              "type": "json"
            },
            "metrics": [
              {
                "name": "Eval loss (epoch 3)",
                "type": "loss",
                "value": 0.1614,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 2)",
                "type": "loss",
                "value": 0.1934,
                "verified": false
              },
              {
                "name": "Eval loss (epoch 1)",
                "type": "loss",
                "value": 0.3627,
                "verified": false
              }
            ],
            "task": {
              "name": "Causal language modeling (teacher-forced eval)",
              "type": "text-generation"
            }
          }
        ]
      }
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "llama",
      "llama-3.2",
      "unsloth",
      "qlora",
      "peft",
      "lora",
      "gguf",
      "semiconductor",
      "technical-writing",
      "product-brief",
      "datasheet",
      "user-guide"
    ]
  },
  "createdAt": "2026-09-14T00:02:59.000Z",
  "downloads": 5792,
  "gated": false,
  "id": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "lastModified": "2026-09-15T15:20:42.000Z",
  "library_name": "transformers",
  "likes": 1,
  "modelId": "Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "7d25743cfe34a261ceec61bf49c01ab80aac7685",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "chat_template.jinja"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "model-00001-of-00002.safetensors"
    },
    {
      "rfilename": "model-00002-of-00002.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "tags": [
    "transformers",
    "safetensors",
    "llama",
    "text-generation",
    "llama-3.2",
    "unsloth",
    "qlora",
    "peft",
    "lora",
    "gguf",
    "semiconductor",
    "technical-writing",
    "product-brief",
    "datasheet",
    "user-guide",
    "conversational",
    "en",
    "base_model:meta-llama/Llama-3.2-3B-Instruct",
    "base_model:finetune:meta-llama/Llama-3.2-3B-Instruct",
    "license:llama3.2",
    "model-index",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ]
}

Text

This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth.