RichardErkhov/h2oai_-_h2ogpt-4096-llama2-13b-chat-gguf

Quantization made by Richard Erkhov.

h2ogpt-4096-llama2-13b-chat - GGUF

Model creator: https://huggingface.co/h2oai/
Original model: https://huggingface.co/h2oai/h2ogpt-4096-llama2-13b-chat/

Name	Quant method	Size
h2ogpt-4096-llama2-13b-chat.Q2_K.gguf	Q2_K	4.52GB
h2ogpt-4096-llama2-13b-chat.IQ3_XS.gguf	IQ3_XS	4.99GB
h2ogpt-4096-llama2-13b-chat.IQ3_S.gguf	IQ3_S	5.27GB
h2ogpt-4096-llama2-13b-chat.Q3_K_S.gguf	Q3_K_S	5.27GB
h2ogpt-4096-llama2-13b-chat.IQ3_M.gguf	IQ3_M	5.57GB
h2ogpt-4096-llama2-13b-chat.Q3_K.gguf	Q3_K	5.9GB
h2ogpt-4096-llama2-13b-chat.Q3_K_M.gguf	Q3_K_M	5.9GB
h2ogpt-4096-llama2-13b-chat.Q3_K_L.gguf	Q3_K_L	6.45GB
h2ogpt-4096-llama2-13b-chat.IQ4_XS.gguf	IQ4_XS	6.54GB
h2ogpt-4096-llama2-13b-chat.Q4_0.gguf	Q4_0	6.86GB
h2ogpt-4096-llama2-13b-chat.IQ4_NL.gguf	IQ4_NL	6.9GB
h2ogpt-4096-llama2-13b-chat.Q4_K_S.gguf	Q4_K_S	6.91GB
h2ogpt-4096-llama2-13b-chat.Q4_K.gguf	Q4_K	7.33GB
h2ogpt-4096-llama2-13b-chat.Q4_K_M.gguf	Q4_K_M	7.33GB
h2ogpt-4096-llama2-13b-chat.Q4_1.gguf	Q4_1	7.61GB
h2ogpt-4096-llama2-13b-chat.Q5_0.gguf	Q5_0	8.36GB
h2ogpt-4096-llama2-13b-chat.Q5_K_S.gguf	Q5_K_S	8.36GB
h2ogpt-4096-llama2-13b-chat.Q5_K.gguf	Q5_K	8.6GB
h2ogpt-4096-llama2-13b-chat.Q5_K_M.gguf	Q5_K_M	8.6GB
h2ogpt-4096-llama2-13b-chat.Q5_1.gguf	Q5_1	9.1GB
h2ogpt-4096-llama2-13b-chat.Q6_K.gguf	Q6_K	9.95GB

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 13B Chat.

Try it live on our h2oGPT demo with side-by-side LLM comparisons and private document chat!

See how it compares to other models on our LLM Leaderboard!

See more at H2O.ai

Model Architecture

LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 5120, padding_idx=0)
    (layers): ModuleList(
      (0-39): 40 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=5120, out_features=5120, bias=False)
          (k_proj): Linear(in_features=5120, out_features=5120, bias=False)
          (v_proj): Linear(in_features=5120, out_features=5120, bias=False)
          (o_proj): Linear(in_features=5120, out_features=5120, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=5120, out_features=13824, bias=False)
          (up_proj): Linear(in_features=5120, out_features=13824, bias=False)
          (down_proj): Linear(in_features=13824, out_features=5120, bias=False)
          (act_fn): SiLUActivation()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=5120, out_features=32000, bias=False)
)