Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


h2ogpt-4096-llama2-7b - GGUF
- Model creator: https://huggingface.co/h2oai/
- Original model: https://huggingface.co/h2oai/h2ogpt-4096-llama2-7b/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [h2ogpt-4096-llama2-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q2_K.gguf) | Q2_K | 2.36GB |
| [h2ogpt-4096-llama2-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [h2ogpt-4096-llama2-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [h2ogpt-4096-llama2-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [h2ogpt-4096-llama2-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [h2ogpt-4096-llama2-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q3_K.gguf) | Q3_K | 3.07GB |
| [h2ogpt-4096-llama2-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [h2ogpt-4096-llama2-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [h2ogpt-4096-llama2-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [h2ogpt-4096-llama2-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q4_0.gguf) | Q4_0 | 3.56GB |
| [h2ogpt-4096-llama2-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [h2ogpt-4096-llama2-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [h2ogpt-4096-llama2-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q4_K.gguf) | Q4_K | 3.8GB |
| [h2ogpt-4096-llama2-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [h2ogpt-4096-llama2-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q4_1.gguf) | Q4_1 | 3.95GB |
| [h2ogpt-4096-llama2-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q5_0.gguf) | Q5_0 | 4.33GB |
| [h2ogpt-4096-llama2-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [h2ogpt-4096-llama2-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q5_K.gguf) | Q5_K | 4.45GB |
| [h2ogpt-4096-llama2-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [h2ogpt-4096-llama2-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q5_1.gguf) | Q5_1 | 4.72GB |
| [h2ogpt-4096-llama2-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q6_K.gguf) | Q6_K | 5.15GB |
| [h2ogpt-4096-llama2-7b.Q8_0.gguf](https://huggingface.co/RichardErkhov/h2oai_-_h2ogpt-4096-llama2-7b-gguf/blob/main/h2ogpt-4096-llama2-7b.Q8_0.gguf) | Q8_0 | 6.67GB |




Original model description:
---
inference: false
language:
- en
license: llama2
model_type: llama
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
- h2ogpt
---

h2oGPT clone of [Meta's Llama 2 7B](https://huggingface.co/meta-llama/Llama-2-7b-hf).

This model can be fine-tuned with [H2O.ai](https://h2o.ai/) open-source software:
- h2oGPT https://github.com/h2oai/h2ogpt/
- H2O LLM Studio https://h2o.ai/platform/ai-cloud/make/llm-studio/

Try our live [h2oGPT demo](https://gpt.h2o.ai) with side-by-side LLM comparisons and private document chat!


## Model Architecture
```
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLUActivation()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
```