Instructions to use actionpace/EvolCodeLlama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use actionpace/EvolCodeLlama-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="actionpace/EvolCodeLlama-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("actionpace/EvolCodeLlama-7b")
model = AutoModelForCausalLM.from_pretrained("actionpace/EvolCodeLlama-7b")

llama-cpp-python

How to use actionpace/EvolCodeLlama-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="actionpace/EvolCodeLlama-7b",
	filename="EvolCodeLlama-7b_Q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use actionpace/EvolCodeLlama-7b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf actionpace/EvolCodeLlama-7b:Q8_0
# Run inference directly in the terminal:
llama cli -hf actionpace/EvolCodeLlama-7b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf actionpace/EvolCodeLlama-7b:Q8_0
# Run inference directly in the terminal:
llama cli -hf actionpace/EvolCodeLlama-7b:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf actionpace/EvolCodeLlama-7b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf actionpace/EvolCodeLlama-7b:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf actionpace/EvolCodeLlama-7b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf actionpace/EvolCodeLlama-7b:Q8_0

Use Docker

docker model run hf.co/actionpace/EvolCodeLlama-7b:Q8_0

LM Studio
Jan

vLLM

How to use actionpace/EvolCodeLlama-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "actionpace/EvolCodeLlama-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "actionpace/EvolCodeLlama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/actionpace/EvolCodeLlama-7b:Q8_0

SGLang

How to use actionpace/EvolCodeLlama-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "actionpace/EvolCodeLlama-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "actionpace/EvolCodeLlama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "actionpace/EvolCodeLlama-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "actionpace/EvolCodeLlama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use actionpace/EvolCodeLlama-7b with Ollama:
```
ollama run hf.co/actionpace/EvolCodeLlama-7b:Q8_0
```

Unsloth Studio

How to use actionpace/EvolCodeLlama-7b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for actionpace/EvolCodeLlama-7b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for actionpace/EvolCodeLlama-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for actionpace/EvolCodeLlama-7b to start chatting

Atomic Chat new
Docker Model Runner
How to use actionpace/EvolCodeLlama-7b with Docker Model Runner:
```
docker model run hf.co/actionpace/EvolCodeLlama-7b:Q8_0
```

Lemonade

How to use actionpace/EvolCodeLlama-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull actionpace/EvolCodeLlama-7b:Q8_0

Run and chat with the model

lemonade run user.EvolCodeLlama-7b-Q8_0

List all available models

lemonade list

actionpace commited on Nov 11, 2023

Commit

c75fbb2

1 Parent(s): e5ea0a2

Training in progress, epoch 1

Browse files

Files changed (7) hide show

adapter_config.json +28 -0
adapter_model.bin +3 -0
config.json +39 -0
special_tokens_map.json +24 -0
tokenizer.model +3 -0
tokenizer_config.json +43 -0
training_args.bin +3 -0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a7093fd570d84977bbb3b8fad4808a806ebf74a41f6150aa34b05d247a37dd
+size 319977229

config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "_name_or_path": "codellama/CodeLlama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32016
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,43 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e119793adec89e061da62a7de24a1a71fb0682ce4c3e3f95d85eab584ad38284
+size 4539