Feat: Add support for upstream FA2 (#626)
* Feat: Add support for upstream FA2 * chore: add is_falcon_derived_model: true to examples * chore: add config to readme for documentation * feat: add extra model types * fix: remove old falcon flash patch * chore: pin transformers and accelerate
This commit is contained in:
@@ -3,6 +3,7 @@ base_model_config: tiiuae/falcon-7b
|
||||
trust_remote_code: true
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
is_falcon_derived_model: true
|
||||
load_in_8bit: true
|
||||
load_in_4bit: false
|
||||
gptq: false
|
||||
|
||||
@@ -6,6 +6,7 @@ base_model_config: tiiuae/falcon-7b
|
||||
trust_remote_code: true
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
is_falcon_derived_model: true
|
||||
load_in_8bit: false
|
||||
# enable 4bit for QLoRA
|
||||
load_in_4bit: true
|
||||
|
||||
@@ -3,6 +3,7 @@ base_model_config: tiiuae/falcon-7b
|
||||
trust_remote_code: true
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
is_falcon_derived_model: true
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
gptq: false
|
||||
|
||||
Reference in New Issue
Block a user