|
--- |
|
language: en |
|
license: other |
|
tags: |
|
- meta |
|
- GPTQ |
|
- facebook |
|
- llama |
|
- llama2 |
|
base_model: meta-llama/Llama-2-7b-hf |
|
model_name: Llama-2-7b-hf-AutoGPTQ |
|
library: |
|
- Transformers |
|
- GPTQ |
|
model_type: llama |
|
pipeline_tag: text-generation |
|
qunatized_by: twhoool02 |
|
--- |
|
|
|
# Model Card for LlamaForCausalLM( |
|
(model): LlamaModel( |
|
(embed_tokens): Embedding(32000, 4096) |
|
(layers): ModuleList( |
|
(0-31): 32 x LlamaDecoderLayer( |
|
(self_attn): LlamaSdpaAttention( |
|
(rotary_emb): LlamaRotaryEmbedding() |
|
(k_proj): QuantLinear() |
|
(o_proj): QuantLinear() |
|
(q_proj): QuantLinear() |
|
(v_proj): QuantLinear() |
|
) |
|
(mlp): LlamaMLP( |
|
(act_fn): SiLU() |
|
(down_proj): QuantLinear() |
|
(gate_proj): QuantLinear() |
|
(up_proj): QuantLinear() |
|
) |
|
(input_layernorm): LlamaRMSNorm() |
|
(post_attention_layernorm): LlamaRMSNorm() |
|
) |
|
) |
|
(norm): LlamaRMSNorm() |
|
) |
|
(lm_head): Linear(in_features=4096, out_features=32000, bias=False) |
|
) |
|
|
|
## Model Details |
|
|
|
This model is a GPTQ quantized version of the meta-llama/Llama-2-7b-hf model. |
|
|
|
- **Developed by:** Ted Whooley |
|
- **Library:** Transformers, GPTQ |
|
- **Model type:** llama |
|
- **Model name:** LlamaForCausalLM( |
|
(model): LlamaModel( |
|
(embed_tokens): Embedding(32000, 4096) |
|
(layers): ModuleList( |
|
(0-31): 32 x LlamaDecoderLayer( |
|
(self_attn): LlamaSdpaAttention( |
|
(rotary_emb): LlamaRotaryEmbedding() |
|
(k_proj): QuantLinear() |
|
(o_proj): QuantLinear() |
|
(q_proj): QuantLinear() |
|
(v_proj): QuantLinear() |
|
) |
|
(mlp): LlamaMLP( |
|
(act_fn): SiLU() |
|
(down_proj): QuantLinear() |
|
(gate_proj): QuantLinear() |
|
(up_proj): QuantLinear() |
|
) |
|
(input_layernorm): LlamaRMSNorm() |
|
(post_attention_layernorm): LlamaRMSNorm() |
|
) |
|
) |
|
(norm): LlamaRMSNorm() |
|
) |
|
(lm_head): Linear(in_features=4096, out_features=32000, bias=False) |
|
) |
|
- **Pipeline tag:** text-generation |
|
- **Qunatized by:** twhoool02 |
|
- **Language(s) (NLP):** en |
|
- **License:** other |
|
|
