Instructions to use timpal0l/Mistral-7B-v0.1-flashback-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timpal0l/Mistral-7B-v0.1-flashback-v2 with Transformers:

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

pipe = pipeline("text-generation", model="timpal0l/Mistral-7B-v0.1-flashback-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("timpal0l/Mistral-7B-v0.1-flashback-v2")
model = AutoModelForCausalLM.from_pretrained("timpal0l/Mistral-7B-v0.1-flashback-v2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timpal0l/Mistral-7B-v0.1-flashback-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timpal0l/Mistral-7B-v0.1-flashback-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timpal0l/Mistral-7B-v0.1-flashback-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/timpal0l/Mistral-7B-v0.1-flashback-v2

SGLang

How to use timpal0l/Mistral-7B-v0.1-flashback-v2 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 "timpal0l/Mistral-7B-v0.1-flashback-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timpal0l/Mistral-7B-v0.1-flashback-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "timpal0l/Mistral-7B-v0.1-flashback-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timpal0l/Mistral-7B-v0.1-flashback-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use timpal0l/Mistral-7B-v0.1-flashback-v2 with Docker Model Runner:
```
docker model run hf.co/timpal0l/Mistral-7B-v0.1-flashback-v2
```

timpal0l

leaderboard-pr-bot commited on Mar 4, 2024

Commit

d84a019

verified ·

1 Parent(s): 4e5eb39

Adding Evaluation Results (#3)

Browse files

- Adding Evaluation Results (c4695dbb083ef79729e1636c442d868f6965ea47)

Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +119 -3

README.md CHANGED Viewed

@@ -5,16 +5,119 @@ language:
 - 'no'
 - da
 license: mit
-models:
-  - timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
 tags:
 - pretrained
 - flashback
 - web
 - conversational
 pipeline_tag: text-generation
 widget:
 - text: Jag tycker att det är roligt med
 ---
 # 🐈‍⬛ Mistral-7B-v0.1-flashback-v2
@@ -180,4 +283,17 @@ Tack och lov för apparna som jag kunde leda oss efter. Att åka kollektivt hade
 Tack ska ni ha för tipsen, igen. Tack till Stockholm för att ni tog emot oss med respekt han var så nöjd med resan.
 Hej så länge, vi kommer åter i framtiden! 😁
-```

 - 'no'
 - da
 license: mit
 tags:
 - pretrained
 - flashback
 - web
 - conversational
+models:
+- timpal0l/Mistral-7B-v0.1-flashback-v2-instruct
 pipeline_tag: text-generation
 widget:
 - text: Jag tycker att det är roligt med
+model-index:
+- name: Mistral-7B-v0.1-flashback-v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 57.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 80.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 59.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 40.66
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 77.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 29.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=timpal0l/Mistral-7B-v0.1-flashback-v2
+      name: Open LLM Leaderboard
 ---
 # 🐈‍⬛ Mistral-7B-v0.1-flashback-v2
 Tack ska ni ha för tipsen, igen. Tack till Stockholm för att ni tog emot oss med respekt han var så nöjd med resan.
 Hej så länge, vi kommer åter i framtiden! 😁
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_timpal0l__Mistral-7B-v0.1-flashback-v2)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.53|
+|AI2 Reasoning Challenge (25-Shot)|57.17|
+|HellaSwag (10-Shot)              |80.74|
+|MMLU (5-Shot)                    |59.98|
+|TruthfulQA (0-shot)              |40.66|
+|Winogrande (5-shot)              |77.19|
+|GSM8k (5-shot)                   |29.42|