h2oai
/

h2ogpt-gm-oasst1-en-2048-falcon-40b-v2

Text Generation

large language model

text-generation-inference

Model card Files Files and versions Community

psinger commited on Jun 23, 2023

Commit

05997ff

•

1 Parent(s): 56a3404

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -49,14 +49,14 @@ quantization_config = BitsAndBytesConfig(
 model_kwargs["quantization_config"] = quantization_config
 tokenizer = AutoTokenizer.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 generate_text = pipeline(
-    model="psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     tokenizer=tokenizer,
     torch_dtype=torch.float16,
     trust_remote_code=True,
@@ -103,13 +103,13 @@ quantization_config = BitsAndBytesConfig(
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     trust_remote_code=True,
     torch_dtype=torch.float16,
     device_map={"": "cuda:0"},
@@ -148,13 +148,13 @@ quantization_config = BitsAndBytesConfig(
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
-    "psinger/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     trust_remote_code=True,
     torch_dtype=torch.float16,
     device_map={"": "cuda:0"},

 model_kwargs["quantization_config"] = quantization_config
 tokenizer = AutoTokenizer.from_pretrained(
+    "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 generate_text = pipeline(
+    model="h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     tokenizer=tokenizer,
     torch_dtype=torch.float16,
     trust_remote_code=True,
 )
 tokenizer = AutoTokenizer.from_pretrained(
+    "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
+    "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     trust_remote_code=True,
     torch_dtype=torch.float16,
     device_map={"": "cuda:0"},
 )
 tokenizer = AutoTokenizer.from_pretrained(
+    "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     use_fast=False,
     padding_side="left",
     trust_remote_code=True,
 )
 model = AutoModelForCausalLM.from_pretrained(
+    "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
     trust_remote_code=True,
     torch_dtype=torch.float16,
     device_map={"": "cuda:0"},