phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 15:23:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

minor fixes

Browse source
This commit is contained in:
Hardik Shah 2024-08-06 18:56:22 -07:00
parent f83b97992c
commit ade574a0ef
4 changed files with 4 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_toolchain/cli/distribution/configure.py
View file

@ -102,8 +102,8 @@ def configure_llama_distribution(dist: "Distribution", config: Dict[str, Any]):
} }
dist_config = { dist_config = {
"providers": provider_configs,
**existing_config, **existing_config,
"providers": provider_configs,
} }
config_path = DISTRIBS_BASE_DIR / existing_config["name"] / "config.yaml" config_path = DISTRIBS_BASE_DIR / existing_config["name"] / "config.yaml"

4
llama_toolchain/cli/model/describe.py
View file

@ -49,9 +49,9 @@ class ModelDescribe(Subcommand):
rows = [ rows = [
( (
colored("Model", "white", attrs=["bold"]), colored("Model", "white", attrs=["bold"]),
colored(model.sku.value, "white", attrs=["bold"]), colored(model.descriptor(), "white", attrs=["bold"]),
), ),
("HuggingFace ID", model.huggingface_id or "<Not Available>"), ("HuggingFace ID", model.huggingface_repo or "<Not Available>"),
("Description", model.description_markdown), ("Description", model.description_markdown),
("Context Length", f"{model.max_seq_length // 1024}K tokens"), ("Context Length", f"{model.max_seq_length // 1024}K tokens"),
("Weights format", model.quantization_format.value), ("Weights format", model.quantization_format.value),

2
llama_toolchain/cli/table.py
View file

@ -45,7 +45,7 @@ def format_row(row, col_widths):
def print_table(rows, headers=None, separate_rows: bool = False): def print_table(rows, headers=None, separate_rows: bool = False):
def itemlen(item): def itemlen(item):
return len(strip_ansi_colors(item)) return max([len(line) for line in strip_ansi_colors(item).split("\n")])
rows = [[x or "" for x in row] for row in rows] rows = [[x or "" for x in row] for row in rows]
if not headers: if not headers:

1
llama_toolchain/inference/client.py
View file

@ -50,7 +50,6 @@ class InferenceClient(Inference):
headers={"Content-Type": "application/json"}, headers={"Content-Type": "application/json"},
timeout=20, timeout=20,
) as response: ) as response:
print("Headers", response.headers)
if response.status_code != 200: if response.status_code != 200:
content = await response.aread() content = await response.aread()
cprint( cprint(