commit 6c3b8a0dd1038ff349b435c95970cf5257a72476 Author: ModelHub XC Date: Thu Jun 4 04:48:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RichardErkhov/dfurman_-_LLaMA-7B-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..baaf687 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +LLaMA-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-7B.IQ3_M.gguf b/LLaMA-7B.IQ3_M.gguf new file mode 100644 index 0000000..52f8d08 --- /dev/null +++ b/LLaMA-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4003f8d7424c12a6ac056873a82626f5daf18a8753f5ca38bf3d9a937b76d3b0 +size 3114864384 diff --git a/LLaMA-7B.IQ3_S.gguf b/LLaMA-7B.IQ3_S.gguf new file mode 100644 index 0000000..3d36e8c --- /dev/null +++ b/LLaMA-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b6f9986fc4ef88e4ef8b715ef3ea43a76d74fb4bf687ff69f9e938ab6d0852 +size 2948304640 diff --git a/LLaMA-7B.IQ3_XS.gguf b/LLaMA-7B.IQ3_XS.gguf new file mode 100644 index 0000000..d9c22c5 --- /dev/null +++ b/LLaMA-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a273950488dbcdeb277fa4192f749ba0c2478e1eb354a095ff2b6137a2b6491d +size 2796523264 diff --git a/LLaMA-7B.IQ4_NL.gguf b/LLaMA-7B.IQ4_NL.gguf new file mode 100644 index 0000000..e02a3f3 --- /dev/null +++ b/LLaMA-7B.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa07ed4b603f53cbc841652f51205fc4ce8ea57d40e2f14dad5aff60472926a +size 3848351488 diff --git a/LLaMA-7B.IQ4_XS.gguf b/LLaMA-7B.IQ4_XS.gguf new file mode 100644 index 0000000..2322c42 --- /dev/null +++ b/LLaMA-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd37fc40da6aae80e1b42045dbae8cf09a965007df9a64befea5b6d8ba60aee +size 3647516416 diff --git a/LLaMA-7B.Q2_K.gguf b/LLaMA-7B.Q2_K.gguf new file mode 100644 index 0000000..8bbbd26 --- /dev/null +++ b/LLaMA-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e752ddfb69645153ede851cd47304f26ec9fb0c5e5044598adbe650ea00b7658 +size 2532863744 diff --git a/LLaMA-7B.Q3_K.gguf b/LLaMA-7B.Q3_K.gguf new file mode 100644 index 0000000..fc6af49 --- /dev/null +++ b/LLaMA-7B.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba4df7884ee7a20ffbe44f52a956e37fe030a0d5cdb119e7b84a5705dc0bc64 +size 3298004736 diff --git a/LLaMA-7B.Q3_K_L.gguf b/LLaMA-7B.Q3_K_L.gguf new file mode 100644 index 0000000..4201357 --- /dev/null +++ b/LLaMA-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb3b630ce0b40f0b6eebeb12bb54a62e280841a0a003011852b52cb0073a8e3 +size 3597111040 diff --git a/LLaMA-7B.Q3_K_M.gguf b/LLaMA-7B.Q3_K_M.gguf new file mode 100644 index 0000000..fc6af49 --- /dev/null +++ b/LLaMA-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba4df7884ee7a20ffbe44f52a956e37fe030a0d5cdb119e7b84a5705dc0bc64 +size 3298004736 diff --git a/LLaMA-7B.Q3_K_S.gguf b/LLaMA-7B.Q3_K_S.gguf new file mode 100644 index 0000000..dd0c3b9 --- /dev/null +++ b/LLaMA-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119de0dc4279b8daf0b187d6df92bb78760b8065dec7677888a81991d5aedb8b +size 2948304640 diff --git a/LLaMA-7B.Q4_0.gguf b/LLaMA-7B.Q4_0.gguf new file mode 100644 index 0000000..8dd4519 --- /dev/null +++ b/LLaMA-7B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42525e12bada47c168668fbb5a4f36d1ab32205b272053ddc07e0e565b061038 +size 3825807104 diff --git a/LLaMA-7B.Q4_1.gguf b/LLaMA-7B.Q4_1.gguf new file mode 100644 index 0000000..e9599c9 --- /dev/null +++ b/LLaMA-7B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f963b38ac74ba224cfe2405a4c6b02f0a5bed94057099db06bbaed4ff09d1fcf +size 4238749440 diff --git a/LLaMA-7B.Q4_K.gguf b/LLaMA-7B.Q4_K.gguf new file mode 100644 index 0000000..c534f9b --- /dev/null +++ b/LLaMA-7B.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa65152b9d72e4a79206616ea8ae7ffc634211170a0c05a36599364c709d8f03 +size 4081004288 diff --git a/LLaMA-7B.Q4_K_M.gguf b/LLaMA-7B.Q4_K_M.gguf new file mode 100644 index 0000000..c534f9b --- /dev/null +++ b/LLaMA-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa65152b9d72e4a79206616ea8ae7ffc634211170a0c05a36599364c709d8f03 +size 4081004288 diff --git a/LLaMA-7B.Q4_K_S.gguf b/LLaMA-7B.Q4_K_S.gguf new file mode 100644 index 0000000..58fa29f --- /dev/null +++ b/LLaMA-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b41672a8bb765be90ee6751da5dae205fb634145cfc79a783b34f0f1da9f4f6 +size 3856740096 diff --git a/LLaMA-7B.Q5_0.gguf b/LLaMA-7B.Q5_0.gguf new file mode 100644 index 0000000..a0c4bf4 --- /dev/null +++ b/LLaMA-7B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9a4d98ba3d7f1e014e2500b6ae258ace784571626471f554c4b0c19bc98ea7 +size 4651691776 diff --git a/LLaMA-7B.Q5_1.gguf b/LLaMA-7B.Q5_1.gguf new file mode 100644 index 0000000..e805fac --- /dev/null +++ b/LLaMA-7B.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91127ffd3fd3f7937ede0c76fbbdfd2b42d909a4a68c00ca706c76ab0ed30b4d +size 5064634112 diff --git a/LLaMA-7B.Q5_K.gguf b/LLaMA-7B.Q5_K.gguf new file mode 100644 index 0000000..812dd02 --- /dev/null +++ b/LLaMA-7B.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7b18a55ffe12970cdebe6340b670fd161bfaadd52b527977a85d1c0a40f682 +size 4783156992 diff --git a/LLaMA-7B.Q5_K_M.gguf b/LLaMA-7B.Q5_K_M.gguf new file mode 100644 index 0000000..812dd02 --- /dev/null +++ b/LLaMA-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7b18a55ffe12970cdebe6340b670fd161bfaadd52b527977a85d1c0a40f682 +size 4783156992 diff --git a/LLaMA-7B.Q5_K_S.gguf b/LLaMA-7B.Q5_K_S.gguf new file mode 100644 index 0000000..e7290e6 --- /dev/null +++ b/LLaMA-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa87ae98216c72198bc059fe4ca808c5b6502513b594e9e88186ddce0f762e29 +size 4651691776 diff --git a/LLaMA-7B.Q6_K.gguf b/LLaMA-7B.Q6_K.gguf new file mode 100644 index 0000000..5a0c6d0 --- /dev/null +++ b/LLaMA-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f329367d1d9ecc26c6c23c44334384163225ac07bedf692b6fedb9ec257ae73e +size 5529194240 diff --git a/LLaMA-7B.Q8_0.gguf b/LLaMA-7B.Q8_0.gguf new file mode 100644 index 0000000..8be9e11 --- /dev/null +++ b/LLaMA-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a33550755426363362cc66a9bd0f2d094faaff74dd1a8a3fed181d5c25b047 +size 7161089792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9be736f --- /dev/null +++ b/README.md @@ -0,0 +1,156 @@ +Quantization made by Richard Erkhov. + +[Github](https://github.com/RichardErkhov) + +[Discord](https://discord.gg/pvy7H8DZMG) + +[Request more models](https://github.com/RichardErkhov/quant_request) + + +LLaMA-7B - GGUF +- Model creator: https://huggingface.co/dfurman/ +- Original model: https://huggingface.co/dfurman/LLaMA-7B/ + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [LLaMA-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q2_K.gguf) | Q2_K | 2.36GB | +| [LLaMA-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.IQ3_XS.gguf) | IQ3_XS | 2.6GB | +| [LLaMA-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.IQ3_S.gguf) | IQ3_S | 2.75GB | +| [LLaMA-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q3_K_S.gguf) | Q3_K_S | 2.75GB | +| [LLaMA-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.IQ3_M.gguf) | IQ3_M | 2.9GB | +| [LLaMA-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q3_K.gguf) | Q3_K | 3.07GB | +| [LLaMA-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q3_K_M.gguf) | Q3_K_M | 3.07GB | +| [LLaMA-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q3_K_L.gguf) | Q3_K_L | 3.35GB | +| [LLaMA-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.IQ4_XS.gguf) | IQ4_XS | 3.4GB | +| [LLaMA-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q4_0.gguf) | Q4_0 | 3.56GB | +| [LLaMA-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.IQ4_NL.gguf) | IQ4_NL | 3.58GB | +| [LLaMA-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q4_K_S.gguf) | Q4_K_S | 3.59GB | +| [LLaMA-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q4_K.gguf) | Q4_K | 3.8GB | +| [LLaMA-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q4_K_M.gguf) | Q4_K_M | 3.8GB | +| [LLaMA-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q4_1.gguf) | Q4_1 | 3.95GB | +| [LLaMA-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q5_0.gguf) | Q5_0 | 4.33GB | +| [LLaMA-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q5_K_S.gguf) | Q5_K_S | 4.33GB | +| [LLaMA-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q5_K.gguf) | Q5_K | 4.45GB | +| [LLaMA-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q5_K_M.gguf) | Q5_K_M | 4.45GB | +| [LLaMA-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q5_1.gguf) | Q5_1 | 4.72GB | +| [LLaMA-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q6_K.gguf) | Q6_K | 5.15GB | +| [LLaMA-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/dfurman_-_LLaMA-7B-gguf/blob/main/LLaMA-7B.Q8_0.gguf) | Q8_0 | 6.67GB | + + + + +Original model description: +--- +pipeline_tag: text-generation +license: other +--- + + +
+ + + +
+ + + +# LLaMA-7B + +LLaMA-7B is a base model for text generation with 6.7B parameters and a 1T token training corpus. It was built and released by the FAIR team at Meta AI alongside the paper "[LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)". + +This model repo was converted to work with the transformers package. It is under a bespoke **non-commercial** license, please see the [LICENSE](https://huggingface.co/dfurman/llama-7b/blob/main/LICENSE) file for more details. + +## Model Summary + +- **Model Type:** Causal decoder-only. +- **Dataset:** The model was trained on 1T tokens using the following data sources: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. +- **Language(s):** The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. +- **License:** Bespoke non-commercial license, see [LICENSE](https://huggingface.co/dfurman/llama-7b/blob/main/LICENSE) file. +- **Model date:** LLaMA was trained between Dec 2022 and Feb 2023. + +**Where to send inquiries about the model:** +Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project, by opening an issue. + +## Intended use +**Primary intended uses:** +The primary use of LLaMA is research on large language models, including: exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, and hallucinations. + +**Primary intended users:** +The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence. + +**Out-of-scope use cases:** +LLaMA is a base model, also known as a foundation model. As such, it should not be used on downstream applications without further risk evaluation, mitigation, and additional fine-tuning. In particular, the model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers. + +## Factors +**Relevant factors:** +One of the most relevant factors for which model performance may vary is which language is used. Although 20 languages were included in the training data, most of the LLaMA dataset is made of English text, and the model is thus expected to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, which is likely also the case for LLaMA. + +**Evaluation factors:** +As LLaMA is trained on data from the Web, it is expected that the model reflects biases from this source. The RAI datasets are thus used to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. The toxicity of model generations is also measured, depending on the toxicity of the context used to prompt the model. + +## Ethical considerations +**Data:** +The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. LLaMA is thus expected to exhibit such biases from the training data. + +**Human life:** +The model is not intended to inform decisions about matters central to human life, and should not be used in such a way. + +**Mitigations:** +The data was filtered from the Web based on its proximity to Wikipedia text and references. For this, the Kneser-Ney language model is used with a fastText linear classifier. + +**Risks and harms:** +Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. LLaMA is not expected to be an exception in this regard. + +**Use cases:** +LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content. + +## How to Get Started with the Model + +### Setup +```python +!pip install -q -U transformers accelerate torch +``` +### GPU Inference in fp16 + +This requires a GPU with at least 15GB of VRAM. + +### First, Load the Model + +```python +import transformers +import torch + +model_name = "dfurman/llama-7b" + +tokenizer = transformers.AutoTokenizer.from_pretrained(model_name) +streamer = transformers.TextStreamer(tokenizer) + +model = transformers.LlamaForCausalLM.from_pretrained( + model_name, + torch_dtype=torch.bfloat16, + device_map="auto" +) +``` + +### Next, Run the Model + +```python +prompt = "An increasing sequence: one," + +inputs = tokenizer( + prompt, + padding=True, + truncation=True, + return_tensors='pt', + return_token_type_ids=False, +).to("cuda") + +_ = model.generate( + **inputs, + max_new_tokens=20, + streamer=streamer, +) +``` + +