InstructCell-instruct

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")

from mmllm.module import InstructCell
import anndata
import numpy as np
from utils import unify_gene_features

# Load the pre-trained InstructCell model from HuggingFace
model = InstructCell.from_pretrained("zjunlp/InstructCell-instruct")

# Load the single-cell data (H5AD format) and gene vocabulary file (numpy format)
adata = anndata.read_h5ad(H5AD_PATH)
gene_vocab = np.load(GENE_VOCAB_PATH)
adata = unify_gene_features(adata, gene_vocab, force_gene_symbol_uppercase=False)

# Select a random single-cell sample and extract its gene counts and metadata
k = np.random.randint(0, len(adata)) 
gene_counts = adata[k, :].X.toarray()
sc_metadata = adata[k, :].obs.iloc[0].to_dict()

# Define the model prompt with placeholders for metadata and gene expression profile
prompt = (
    "Can you help me annotate this single cell from a {species}? " 
    "It was sequenced using {sequencing_method} and is derived from {tissue}. " 
    "The gene expression profile is {input}. Thanks!"
)

# Use the model to generate predictions
for key, value in model.predict(
    prompt, 
    gene_counts=gene_counts, 
    sc_metadata=sc_metadata, 
    do_sample=True, 
    top_p=0.95,
    top_k=50,
    max_new_tokens=256,
).items():
    # Print each key-value pair
    print(f"{key}: {value}")