Update README.md

README.md

@@ -35,7 +35,7 @@ prompt = "<|prompt|>How are you?</s><|answer|>"
 ## Summary
 
 This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
-- Base model: [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)
+- Base model: [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)
 - Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28) personalized
 
 
@@ -54,7 +54,7 @@ import torch
 from transformers import pipeline
 
 generate_text = pipeline(
-    model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b",
+    model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
     torch_dtype="auto",
     trust_remote_code=True,
     use_fast=False,
@@ -92,13 +92,13 @@ from h2oai_pipeline import H2OTextGenerationPipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained(
-    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b",
+    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
-    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b",
+    "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
     torch_dtype="auto",
     device_map={"": "cuda:0"},
     trust_remote_code=True,
@@ -124,7 +124,7 @@ You may also construct the pipeline from the loaded model and tokenizer yourself
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b"  # either local folder or huggingface model name
+model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
 prompt = "<|prompt|>How are you?</s><|answer|>"
@@ -165,20 +165,20 @@ print(answer)
 ```
 LlamaForCausalLM(
   (model): LlamaModel(
-    (embed_tokens): Embedding(32000, 5120, padding_idx=0)
+    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
     (layers): ModuleList(
-      (0-39): 40 x LlamaDecoderLayer(
+      (0-31): 32 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)
+          (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=5120, out_features=13824, bias=False)
-          (down_proj): Linear(in_features=13824, out_features=5120, bias=False)
-          (up_proj): Linear(in_features=5120, out_features=13824, bias=False)
+          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
+          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
+          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
           (act_fn): SiLUActivation()
         )
         (input_layernorm): LlamaRMSNorm()
@@ -187,7 +187,7 @@ LlamaForCausalLM(
     )
     (norm): LlamaRMSNorm()
   )
-  (lm_head): Linear(in_features=5120, out_features=32000, bias=False)
+  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
 )
 ```